Rycolab

Logical Aspects of Computation

Fri, 20 Feb 2026 00:00:00 +0000

A Close Analysis of the Subset Construction

Mon, 01 Dec 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Machine Learning and Computational Complexity, Fall 2025

Fri, 26 Sep 2025 00:00:00 +0000

Investigating Critical Period Effects in Language Acquisition through Neural Language Models

Mon, 01 Sep 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Large Language Models, Spring 2026

Mon, 01 Sep 2025 00:00:00 +0000

Taxonomy-Aware Evaluation of Vision--Language Models

Sun, 01 Jun 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Distributional Perspective on Word Learning in Neural Language Models

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Practical Method for Generating String Counterfactuals

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Are Language Models Efficient Reasoners? A Perspective from Logic Programming

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Better Estimation of the KL Divergence Between Language Models

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Bigger is not always better: The importance of human-scale language modeling for psycholinguistics

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Can Language Models Learn Typologically Implausible Languages?

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Characterizing the Expressivity of Transformer Language Models

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Controllable Context Sensitivity and the Knob Behind It

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Gumbel Counterfactual Generation from Language Models

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

How Persuasive is Your Context?

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Incremental Alternative Sampling as a Lens into the Temporal and Representational Resolution of Linguistic Prediction

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Information Locality as an Inductive Bias for Neural Language Models

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Language Models over Canonical Byte-Pair Encodings

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the challenges and opportunities in generative AI

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Prefix Parsing is Just Parsing

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Probability Distributions Computed by Hard-Attention Transformers

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Syntactic Control of Language Models by Posterior Inference

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Foundations of Tokenization: Statistical and Computational Concerns

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Harmonic Structure of Information Contours

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Training Neural Networks as Recognizers of Formal Languages

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Unique Hard Attention: A Tale of Two Sides

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Variational Best-of-$N$ Alignment

Wed, 01 Jan 2025 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On Affine Homotopy between Language Encoders

Sun, 01 Dec 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Activation Scaling for Steering and Interpreting Language Models

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

An L* Algorithm for Deterministic Weighted Automata

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Can Transformer Language Models Learn $n$-gram Language Models?

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Efficiently Computing Susceptibility to Context in Language Models

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Generalized Measures of Responsive and Anticipatory Language Processing

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Proper Treatment of the Word in Computational Psycholinguistics

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On The Role of Context in Reading Time Prediction

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Reverse-Engineering the Reader

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse

Fri, 01 Nov 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On Efficiently Representing Regular Languages as RNNs

Thu, 01 Aug 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Mon, 01 Jul 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Principled Gradient-Based MCMC for Conditional Sampling of Text

Mon, 01 Jul 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Representation Surgery: Theory and Practice of Affine Steering

Mon, 01 Jul 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Correlation Does Not Imply Compensation: Complexity and Irregularity in the Lexicon

Sat, 01 Jun 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Transformers Can Represent n-gram Language Models

Sat, 01 Jun 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

From Cognitive Modeling to Typological Universals: Investigations with (Large) Language Models

Tue, 28 May 2024 10:30:00 +0200

Bio

Tatsuki Kuribayashi obtained a Ph.D. in information science at Tohoku University, Japan (adviser: Prof. Kentaro Inui) and started a Postdoc at MBZUAI, UAE, in 2023 (adviser: Prof. Timothy Baldwin). His research focuses on the intersection between natural language processing (NLP) and the cognitive science of language, along with the contribution to works on the interpretability of NLP models, automatic writing assistance, and neuro-symbolic reasoning of NLP models. He is an organizer of the Cognitive Modeling and Computational Linguistics Workshop (CMCL 2024). His co-authored works are recognized with Best Paper Awards in AACL-SRW 2022, ACL-SRW 2023, and a spotlight paper in ICLR 2024.

An information-theoretic analysis of targeted regressions during reading

Wed, 01 May 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

PILA: A Historical-Linguistic Dataset of Proto-Italic and Latin

Wed, 01 May 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns

Wed, 01 May 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Entity Tracking in Language Models

Mon, 22 Apr 2024 10:30:00 +0200

Bio

Sebastian Schuster is a lecturer in computational linguistics at University College London. His main research interest is in computational semantics and pragmatics, particularly developing formal and psycholinguistic accounts of pragmatic language use and more reliable natural language understanding systems.

Social Science as a Problem Space for NLP

Thu, 21 Mar 2024 15:00:00 +0200

Bio

Alexander Hoyle is a PhD student in Computer Science at the University of Maryland, advised by Philip Resnik. His research is focused on the development and evaluation of NLP methods for computational social science. His work has appeared at conferences including ACL, EMNLP, NAACL, and NeurIPS. In the past, he has interned with the Fairness, Accountability, and Transparency group at Microsoft Research and the AllenNLP team at the Allen Institute for Artificial Intelligence.

A Transformer with Stack Attention

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Context versus Prior Knowledge in Language Models

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Direct Preference Optimization with an Offset

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Grammatical Gender's Influence on Distributional Semantics: A Causal Perspective

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Large-scale evidence for logarithmic effects of word predictability on reading time

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Lower Bounds on the Expressivity of Recurrent Neural Language Models

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

NARRATE: Versatile Language Architecture for Optimal Control in Robotics

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Ethics of Automating Legal Actors

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Foundations of Tokenization: Statistical and Computational Concerns

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Role of $n$-gram Smoothing in the Age of Neural Networks

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards Explainability in Legal Outcome Prediction Models

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

What Do Language Models Learn in Context? The Structured Task Hypothesis.

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

When is a Language Process a Language Model?

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

An Exploration of Left-Corner Transformations

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Efficient Algorithms for Recognizing Weighted Tree-Adjoining Languages

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Language Model Quality Correlates with Psychometric Predictive Power in Multiple Languages

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Optimality of Word Lengths

Fri, 01 Dec 2023 00:00:00 +0000

On the Representational Capacity of Recurrent Neural Language Models

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Quantifying the redundancy between prosody and text

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Recurrent Neural Language Models as Probabilistic Finite-state Automata

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Revisiting the Optimality of Word Lengths

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Structured Voronoi Sampling

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Ethics of Automating Legal Actors

Fri, 01 Dec 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution

Wed, 22 Nov 2023 11:00:00 +0200

Bio

Jaap Jumelet is a PhD candidate in the group of Jelle Zuidema at the ILLC, University of Amsterdam. The topic of his PhD lies at the intersection of explainable AI and natural language processing. He is interested in uncovering the linguistic capacities of current NLP models, and developing new techniques that allow to gain these insights in a robust and faithful way.

Modeling Sequences with Quantum States

Wed, 08 Nov 2023 10:30:00 +0200

Bio

John Terilla is Professor of Mathematics at Queens College and on the Doctoral Faculty at the City University of New York Graduate Center. His research is in algebraic topology, quantum physics, and artificial intelligence, and he is interested in understanding the mathematics at work in natural language.

A Fast Algorithm for Computing Prefix Probabilities

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Formal Perspective on Byte-Pair Encoding

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Measure-theoretic Characterization of Tight Language Model

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

An Ordinal Latent Variable Model of Conflict Intensity

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Convergence and Diversity in the Control Hierarchy

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels

Sat, 01 Jul 2023 00:00:00 +0000

Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Efficient Semiring-Weighted Earley Parsing

Sat, 01 Jul 2023 00:00:00 +0000

Efficient Semiring-Weighted Earley Parsing

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Generalizing Backpropagation for Gradient-Based Interpretability

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Generalizing Backpropagation for Gradient-Based Interpretability

Sat, 01 Jul 2023 00:00:00 +0000

Hexatagging: Projective Dependency Parsing as Tagging

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Locally Typical Sampling

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Locally Typical Sampling

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Log-Linear Guardedness and Its Implications

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Naturalistic Causal Probing for Morpho-Syntax

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Naturalistic Causal Probing for Morpho-Syntax

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Effect of Anticipation on Reading Times

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Efficacy of Sampling Adapters

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Testing the Predictions of Surprisal Theory in 11 Languages

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Tokenization and the Noiseless Channel

Sat, 01 Jul 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

MAUVE Scores for Generative Models: Theory and Practice

Fri, 16 Jun 2023 14:00:00 +0200

Bio

Krishna Pillutla is a visiting researcher (postdoc) at Google Research in the Federated Learning team. He is broadly interested in machine learning, artificial intelligence, optimization, robustness, and privacy, and specifically in the setting of federated learning, and text generation. He obtained his PhD from the Paul G. Allen School of Computer Science & Engineering at the University of Washington.

Data Governance and Transparency for Large Language Models

Fri, 09 Jun 2023 14:30:00 +0200

Bio

Anna Rogers is an assistant professor in the Computer Science Department at the IT University of Copenhagen. She has a wide range of research interests that span intersection of linguistics, natural language processing, and machine learning. She is also currently a co-program-chair of ACL 2023.

The Evolution of Automatic Metrics, From String Matching to Black-Box LLM

Wed, 24 May 2023 10:30:00 +0200

Bio

Tom Kocmi is a researcher at Microsoft Translator focusing on human and automatic evaluation of machine translation. He coordinates the annual WMT General MT shared task where researchers from both academia and industry compete to build the best performing MT systems.

On the alignment of production variability in humans and text generators

Wed, 03 May 2023 10:30:00 +0200

Bio

Mario Giulianelli is a PhD student at the Institute for Logic, Language and Computation of the University of Amsterdam. His research is mainly on human strategies of communication using computational models of language understanding and generation.

On the Intersection of Context-Free and Regular Languages

Mon, 01 May 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation

Mon, 01 May 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Sentiment as an Ordinal Latent Variable

Mon, 01 May 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Communicative Feedback in Language Acquisition

Tue, 04 Apr 2023 10:30:00 +0200

Bio

Mitja Nikolaus is currently finishing his PhD with Abdellah Fourtassi at Aix-Marseille University. Mitja is a cognitive scientist who uses machine learning to study how children acquire language. He’s especially interested in communicative feedback and multimodal learning.

The Ordered Matrix Dirichlet for State-Space Models

Sat, 01 Apr 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

"Ambiguous" isn't "Underspecified": Evidence from three tasks

Thu, 02 Mar 2023 13:30:00 +0200

Bio

Shayne Sloggett has been the Experimental Officer in Psycholinguistics at the University of York’s Department of Language and Linguistic Science since September 2019. His research interests are sentence processing, syntax, and the interaction of grammatical knowledge and sentence comprehension routines. This research draws on insights from linguistic theory to better inform psycholinguistic models (and vice versa), using a range of methods from formal acceptability rating tasks, to eye-tracking while reading and corpus linguistics.

Everything is a Construction: New Goals for Syntactic and Semantic Probing

Wed, 01 Mar 2023 13:30:00 +0200

Bio

Leonie Weissweiler is a PhD student in Computational Linguistics at LMU Munich, working with Hinrich Schütze, as well as with Lori Levin and David Mortensen at CMU. Her research interests are applying cognitively plausible theories of linguistics to NLP, as well as unsupervised crosslingual computational morphosyntax.

If We Want AI to be Interpretable, We Need to Measure Interpretability

Wed, 11 Jan 2023 14:00:00 +0200

Bio

Jordan Boyd-Graber is an associate professor in the University of Maryland’s Computer Science Department, iSchool, UMIACS, and Language Science Center. He generally works on how humans can interact with AI tools, starting first with topic models, then translation, then negotiation, and most recently question answering. He and his students have won “best of” awards at NIPS (2009, 2015), NAACL (2016), and CoNLL (2015). Jordan also won the British Computing Society’s 2015 Karen Spärk Jones Award and a 2017 NSF CAREER award.

A Cross-Linguistic Pressure for Uniform Information Density in Word Order

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Geometric Notion of Causal Probing

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Latent-Variable Model for Intrinsic Probing

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Controlled Text Generation with Natural Language Instructions

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

LEACE: Perfect linear concept erasure in closed form

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Effect of Anticipation on Reading Times

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Role of Negative Precedent in Legal Outcome Prediction

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Algorithms for Weighted Finite-State Automata with Failure Arcs

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Algorithms for Weighted Pushdown Automata

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Autoregressive Structure Prediction with Language Models

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Kernelized Concept Erasure

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Mutual Information and Hallucinations in Abstractive Summarization

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On Parsing as Tagging

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Architectural Bottleneck Principle

Thu, 01 Dec 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Understanding RNNs and Transformers using Formal Languages

Mon, 21 Nov 2022 14:00:00 +0200

Bio

Sophie Hao is a Faculty Fellow (i.e., a postdoc without a supervisor) in Data Science at New York University. Her research is on interpretability and explanability for natural language processing, with the aim of understanding what it means for a deep neural network to be ‘interpreted by’ or ‘explained to’ a human audience. She recently completed her PhD in Linguistics and Computer Science with Prof. Robert Frank and Prof. Dana Angluin at Yale University.

Collecting Knowledge Graph Explanations for Commonsense QA via Counterfactual Annotation

Fri, 18 Nov 2022 14:00:00 +0200

Bio

Guy Aglionby is a final year PhD student at the University of Cambridge Computer Lab, supervised by Prof Simone Teufel and a member of Homerton College. His PhD research is on developing interpretable models for common sense multi-hop reasoning.

Principles of Compositionality Improve Systematic Generalization of Neural Networks

Wed, 16 Nov 2022 14:00:00 +0200

Bio

Róbert Csordás is a PhD candidate at the Swiss AI lab IDSIA and currently doing an internship at DeepMind. His research interests are systematic generalizationi n the context of algorithmic reasoning and network architectures with nductive biases like information routing (attention, memory) and learning modular structures.

Text Generation with Text-Editing Models

Fri, 28 Oct 2022 09:00:00 +0200

Bio

Eric Malmi is a Senior Research Scientist at Google, Zürich. His research focuses on developing Natural Language Generation (NLG) methods for Google Assistant. He received his PhD (2018) in Computer Science from Aalto University, Finland. During his studies, Eric did internships at Google, Qatar Computing Research Institute, Idiap Research Institute, and CERN.

Searching for Structure in Unfalsifiable Claims

Thu, 27 Oct 2022 14:30:00 +0200

Bio

Serge Belongie is a professor of Computer Science at the University of Copenhagen, where he also serves as the head of the Pioneer Centre for Artificial Intelligence. His research interests include Computer Vision, Machine Learning, Augmented Reality, and Human-in-the-Loop Computing.

CCG on all levels of analysis: Linguistic Universals, Incremental Processing and Brain Activity

Wed, 19 Oct 2022 14:00:00 +0200

Bio

Miloš Stanojević is a Senior Research Scientist in DeepMind. Prior to that he did a PostDoc at University of Edinburgh with Mark Steedman where he worked on Combinatory Categorial Grammars (CCG), and collaborated with Ed Stabler on Minimalist Grammars. He has received a PhD degree from University of Amsterdam for the work on machine translation. His main research interests lie in incremental sentence processing, structured inference, formal grammars, and generative linguistics.

Modular and Composable Transfer Learning

Mon, 17 Oct 2022 13:00:00 +0200

Bio

Jonas Pfeiffer is a Research Scientist at Google Research. He is interested in modular representation learning in multi-task, multilingual, and multi-modal contexts, and in low-resource scenarios. He worked on his PhD at the Technical University of Darmstadt, was a visiting researcher at the New York University and a Research Scientist Intern at Meta Research. Jonas has received the IBM PhD Research Fellowship award for 2021/2022. He has given numerous invited talks at academia, industry and ML summer schools, and has co-organized multiple workshops on multilinguality and multimodality.

Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication

Tue, 04 Oct 2022 14:00:00 +0200

Bio

André Martins (PhD 2012, Carnegie Mellon University and University of Lisbon) is an Associate Professor at Instituto Superior Técnico, University of Lisbon, researcher at Instituto de Telecomunicações, and the VP of AI Research at Unbabel. His research, funded by a ERC Starting Grant (DeepSPIN) and other grants (P2020 project Unbabel4EU and CMU-Portugal project MAIA) include machine translation, quality estimation, structure and interpretability in deep learning systems for NLP. His work has received best paper awards at ACL 2009 (long paper) and ACL 2019 (system demonstration paper). He co-founded and co-organizes the Lisbon Machine Learning School (LxMLS), and he is a Fellow of the ELLIS society.

Benchmarking Compositionality with Formal Languages

Sat, 01 Oct 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Equivariant Transduction through Invariant Alignment

Sat, 01 Oct 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Faster Dependency Parsing, More Accurate Unsupervised Parsing

Fri, 30 Sep 2022 14:00:00 +0200

Bio

Shay Cohen is a Reader at the University of Edinburgh (School of Informatics). Before this, he was a postdoctoral research scientist in the Department of Computer Science at Columbia University and held an NSF/CRA Computing Innovation Fellowship. He received his B.Sc. and M.Sc. from Tel Aviv University in 2000 and 2004, and his Ph.D. from Carnegie Mellon University in 2011. His research interests span a range of topics in natural language processing and machine learning, focusing on structured prediction (for example, parsing) and text generation.

Encoder-decoder manipulations at TartuNLP

Fri, 30 Sep 2022 10:10:00 +0200

Bio

Mark Fišel is head of NLP at University of Tartu (Estonia) with focus on machine translation, speech synthesis, large language model usage, tuning and analysis, etc.

Continual-T0: Fine-tuned Language Models are Continual Learners

Wed, 03 Aug 2022 13:30:00 +0200

Bio

Tuhin Chakrabarty is a PhD student in Computer Science at Columbia University. Within the department he is a part of the Natural Language Processing group, where he is advised by Smaranda Muresan. His research is supported by the Columbia Center of Artificial Intelligence & Technology (CAIT) & Amazon Science Ph.D. Fellowship. His research interests are broadly in Natural Language Processing and Machine Learning, with special focus in Language Generation. His overarching research question centers around how we can control large language models to understand, interpret or generate creative text.Recently he is also working in Continual Learning of Large language models. https://tuhinjubcse.github.io/

How Cognitive Biases Do (and Do Not) Shape Lexicons: Two Computational Studies

Tue, 19 Jul 2022 13:30:00 +0200

Bio

David Mortensen is a computational linguist interested in phonology, morphology, language change, linguistic typology, and human-in-the-loop computation. He is currently a Systems Scientist (a non-tenure track research faculty member at the Assistant Professor level) in the Language Technologies Institute, which is part of Carnegie Mellon University’s School of Computer Science. Before coming to CMU, he was an Assistant Professor in the Department of Linguistics at the University of Pittsburgh.

Losing bits and finding meaning: Efficient compression shapes meaning in language

Mon, 04 Jul 2022 14:00:00 +0200

Bio

Noga Zaslavsky is a postdoc at MIT. Her research aims to understand language, learning, and reasoning from first principles, building on ideas and methods from machine learning and information theory.

A Structured Span Selector

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Exact Paired-Permutation Testing for Structured Test Statistics

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Linear Adversarial Concept Erasure

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Machine Learning of Ethical Judgments from Natural Language

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Probing via Prompting

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SIGMORPHON--UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The SIGMORPHON 2022 Shared Task on Morpheme Segmentation

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes

Fri, 01 Jul 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Assessing the Effects of Friend-to-Friend Texting on Turnout in the 2018 US Midterm Elections

Fri, 10 Jun 2022 16:00:00 +0200

Bio

Aaron Schein is an Assistant Professor in the Department of Statistics and the Data Science Institute at the University of Chicago. His research develops statistical models and computational methods to analyze modern large-scale data in political science, economics, and genetics, among other fields in the social and natural sciences.

Human Language Understanding: Research of the CALCULUS project

Fri, 10 Jun 2022 10:15:00 +0200

Bio

Marie-Francine (Sien) Moens is full professor at the Department of Computer Science at KU Leuven, Belgium. She is the director of the Language Intelligence and Information Retrieval (LIIR) research lab and a member of the Human Computer Interaction group. Her main direction of research is the development of novel methods for automated content recognition in text and multimedia using machine learning and exploiting insights from linguistic and cognitive theories.

Analyzing Wrap-Up Effects through an Information-Theoretic Lens

Sun, 01 May 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Estimating the Entropy of Linguistic Distributions

Sun, 01 May 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the probability-quality paradox in language generation

Sun, 01 May 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Probing as Quantifying the Inductive Bias of Pre-trained Representations

Sun, 01 May 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Probing for the Usage of Grammatical Number

Sun, 01 May 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Syntactic Structure and Transformer Models of Natural Language

Mon, 04 Apr 2022 16:15:00 +0200

Bio

Chris Dyer is a principal scientist with DeepMind in London, UK, and holds an Adjunct Professor appointment in the School of Computer Science at Carnegie Mellon University. His former PhD students have gone on to research positions in major industrial labs, tenure track academic positions (CMU, UC Irvine, USC, and the University of Washington). He is a 2016 recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE). He lives in London and plays the cello.

Thinking like Transformers

Tue, 01 Mar 2022 17:00:00 +0200

Bio

Gail is a PhD student at Technion working with Eran Yahav and Yoav Goldberg. Her research interest is in understanding sequential neural networks (such as RNNs and transformers) through the lens of formal language theory.

An Ordinal Latent Variable Model of Conflict Intensity

Sat, 01 Jan 2022 00:00:00 +0000

Cluster-based Evaluation of Automatically Generated Text

Sat, 01 Jan 2022 00:00:00 +0000

On Decoding Strategies for Neural Text Generators

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Intersection of Context-Free and Regular Languages

Sat, 01 Jan 2022 00:00:00 +0000

State-of-the-art generalisation research in NLP: a taxonomy and review

Sat, 01 Jan 2022 00:00:00 +0000

State-of-the-art generalisation research in NLP: a taxonomy and review

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Visual Comparison of Language Model Adaptation

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Neuro-symbolic Scaffolds for Commonsense Reasoning

Tue, 23 Nov 2021 13:00:00 +0200

Bio

Antoine Bosselut is an assistant professor in the School of Computer and Communication Sciences at EPFL. He leads the EPFL NLP group where they conduct research on natural language processing (NLP) systems that can model, represent, and reason about human and world knowledge.

A Bayesian Framework for Information-Theoretic Probing

Mon, 01 Nov 2021 00:00:00 +0000

A Bayesian Framework for Information-Theoretic Probing

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Bayesian Framework for Information-Theoretic Probing

Mon, 01 Nov 2021 00:00:00 +0000

A Plug-and-Play Method for Controlled Text Generation

Mon, 01 Nov 2021 00:00:00 +0000

A Plug-and-Play Method for Controlled Text Generation

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A surprisal--duration trade-off across and within the world's languages

Mon, 01 Nov 2021 00:00:00 +0000

A surprisal--duration trade-off across and within the world’s languages

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Adjusting the Conflict-Cooperation Scale for Armed Conflict Assessment

Mon, 01 Nov 2021 00:00:00 +0000

Classifying Dyads for Militarized Conflict Analysis

Mon, 01 Nov 2021 00:00:00 +0000

Classifying Dyads for Militarized Conflict Analysis

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Conditional Poisson Stochastic Beam Search

Mon, 01 Nov 2021 00:00:00 +0000

Conditional Poisson Stochastic Beam Search

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Conditional Poisson Stochastic Beams

Mon, 01 Nov 2021 00:00:00 +0000

Efficient Sampling of Dependency Structure

Mon, 01 Nov 2021 00:00:00 +0000

Efficient Sampling of Dependency Structure

Mon, 01 Nov 2021 00:00:00 +0000

Efficient Sampling of Dependency Structure

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Equivariant Transduction through Invariant Alignment

Mon, 01 Nov 2021 00:00:00 +0000

Keyword2Text: A Plug-and-Play Method for Controlled Text Generation

Mon, 01 Nov 2021 00:00:00 +0000

On Homophony and Rényi Entropy

Mon, 01 Nov 2021 00:00:00 +0000

On Homophony and Rényi Entropy

Mon, 01 Nov 2021 00:00:00 +0000

On Homophony and Rényi Entropy

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Phone-level Uniform Information Density across and within Languages

Mon, 01 Nov 2021 00:00:00 +0000

Revisiting the Uniform Information Density Hypothesis

Mon, 01 Nov 2021 00:00:00 +0000

Revisiting the Uniform Information Density Hypothesis

Mon, 01 Nov 2021 00:00:00 +0000

Revisiting the Uniform Information Density Hypothesis

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Searching for More Efficient Dynamic Programs

Mon, 01 Nov 2021 00:00:00 +0000

Searching for More Efficient Dynamic Programs

Mon, 01 Nov 2021 00:00:00 +0000

Searching for More Efficient Dynamic Programs

Mon, 01 Nov 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Text or Topology? Classifying Ally-Enemy Pairs in Militarised Conflict

Mon, 01 Nov 2021 00:00:00 +0000

A cognitive regularizer for language modeling

Sun, 01 Aug 2021 00:00:00 +0000

A cognitive regularizer for language modeling

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Determinantal Beam Search

Sun, 01 Aug 2021 00:00:00 +0000

Determinantal Beam Search

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Examining the Inductive Bias of Neural Language Models with Artificial Languages

Sun, 01 Aug 2021 00:00:00 +0000

Examining the Inductive Bias of Neural Language Models with Artificial Languages

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Higher-order Derivatives of Weighted Finite-state Machines

Sun, 01 Aug 2021 00:00:00 +0000

Higher-order Derivatives of Weighted Finite-state Machines

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Is Sparse Attention more Interpretable?

Sun, 01 Aug 2021 00:00:00 +0000

Is Sparse Attention more Interpretable?

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Language Model Evaluation Beyond Perplexity

Sun, 01 Aug 2021 00:00:00 +0000

Language Model Evaluation Beyond Perplexity

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Modeling the Unigram Distribution

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Modelling the Unigram Distribution

Sun, 01 Aug 2021 00:00:00 +0000

On Finding the $K$-best Non-projective Dependency Trees

Sun, 01 Aug 2021 00:00:00 +0000

On Finding the $K$-best Non-projective Dependency Trees

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages

Sun, 01 Aug 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Non-Linear Structural Probe

Tue, 01 Jun 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Non-Linear Structural Probe

Tue, 01 Jun 2021 00:00:00 +0000

Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing

Tue, 01 Jun 2021 00:00:00 +0000

Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing

Tue, 01 Jun 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Finding Concept-specific Biases in Form--Meaning Associations

Tue, 01 Jun 2021 00:00:00 +0000

Finding Concept-specific Biases in Form--Meaning Associations

Tue, 01 Jun 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

How (Non-)Optimal is the Lexicon?

Tue, 01 Jun 2021 00:00:00 +0000

How (Non-)Optimal is the Lexicon?

Tue, 01 Jun 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SIGTYP 2021 Shared Task: Robust Spoken Language Identification

Tue, 01 Jun 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

What About the Precedent: An Information-Theoretic Analysis of Common Law

Tue, 01 Jun 2021 00:00:00 +0000

What About the Precedent: An Information-Theoretic Analysis of Common Law

Tue, 01 Jun 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

It’s Time for Reasoning

Mon, 26 Apr 2021 16:15:00 +0200

Bio

Dan Roth is the Eduardo D. Glandt Distinguished Professor at the Department of Computer and Information Science, University of Pennsylvania, and a Fellow of the AAAS, the ACM, AAAI, and the ACL. In 2017 Roth was awarded the John McCarthy Award, the highest award the AI community gives to mid-career AI researchers. Roth was recognized “for major conceptual and theoretical advances in the modeling of natural language understanding, machine learning, and reasoning.” Roth has published broadly in machine learning, natural language processing, knowledge representation and reasoning, and learning theory, and has developed advanced machine learning based tools for natural language applications that are being used widely. Until February 2017 Roth was the Editor-in-Chief of the Journal of Artificial Intelligence Research (JAIR). Roth has been involved in several startups; most recently he was a co-founder and chief scientist of NexLP, a startup that leverages the latest advances in Natural Language Processing (NLP), Cognitive Analytics, and Machine Learning in the legal and compliance domains. NexLP was sold to Reveal in 2020. Prof. Roth received his B.A Summa cum laude in Mathematics from the Technion, Israel, and his Ph.D. in Computer Science from Harvard University in 1995.

Applying the Transformer to Character-level Transduction

Thu, 01 Apr 2021 00:00:00 +0000

Applying the Transformer to Character-level Transduction

Thu, 01 Apr 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Disambiguatory signals are stronger in word initial positions

Thu, 01 Apr 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Searching for Search Errors in Neural Morphological Inflection

Thu, 01 Apr 2021 00:00:00 +0000

Searching for Search Errors in Neural Morphological Inflection

Thu, 01 Apr 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Word on Machine Ethics: A Response to Jiang et al. (2021)

Fri, 01 Jan 2021 00:00:00 +0000

Differentiable Subset Pruning of Transformer Heads

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Efficient Computation of Expectations under Spanning Tree Distributions

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Morphologically Aware Word-Level Translation

Tue, 01 Dec 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation

Sun, 01 Nov 2020 00:00:00 +0000

Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Finding Concept-specific Biases in Form–Meaning Associations

Sun, 01 Nov 2020 00:00:00 +0000

If Beam Search is the Answer, What was the Question?

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Intrinsic Probing through Dimension Selection

Sun, 01 Nov 2020 00:00:00 +0000

Intrinsic Probing through Dimension Selection

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Investigating Cross-Linguistic Adjective Ordering Tendencies with a Latent-Variable Model

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Pareto Probing: Trading Off Accuracy for Simplicity

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Please Mind the Root: Decoding Arborescences for Dependency Parsing

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SIGTYP 2020 Shared Task: Prediction of Typological Features

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Speakers Fill Semantic Gaps with Context

Sun, 01 Nov 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Corpus for Large-Scale Phonetic Typology

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Tale of a Probe and a Parser

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Information-Theoretic Probing for Linguistic Structure

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Metaphor Detection Using Context and Concreteness

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Predicting Declension Class from Form and Meaning

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The Paradigm Discovery Problem

Wed, 01 Jul 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Best-First Beam Search

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Efficient Computation of Expectations under Spanning Tree Distributions

Wed, 01 Jan 2020 00:00:00 +0000

On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs

Wed, 01 Jan 2020 00:00:00 +0000

Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages

Wed, 01 Jan 2020 00:00:00 +0000

Phonotactic Complexity and its Trade-offs

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SIGMORPHON 2020 Task 0 System Description: ETH Zürich Team

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

UniMorph 3.0: Universal Morphology

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Don’t Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction

Fri, 01 Nov 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Examining Gender Bias in Languages with Grammatical Gender

Fri, 01 Nov 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Fri, 01 Nov 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Quantifying the Semantic Core of Gender Systems

Fri, 01 Nov 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards Zero-Shot Language Modeling

Fri, 01 Nov 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection

Thu, 01 Aug 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Counterfactual Data Augmentation for Mitigating Gender Bias in Languages with Rich Morphology

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Exact Hard Monotonic Attention for Character-Level Transduction

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Meaning to Form: Measuring Systematicity as Information

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Measuring Morphological Irregularity

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the distribution of deep clausal embeddings: A large cross-linguistic study

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Uncovering Typological Implications with Belief Nets

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Unsupervised Discovery of Gendered Language through Latent-Variable Modeling

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

What Kind of Language Is Hard to Language-Model?

Mon, 01 Jul 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Probabilistic Generative Model of Linguistic Typology

Sat, 01 Jun 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Simple Joint Model for Improved Contextual Neural Lemmatization

Sat, 01 Jun 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Combining Sentiment Lexica with a Multi-View Variational Autoencoder

Sat, 01 Jun 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Contextualization of Morphological Inflection

Sat, 01 Jun 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Gender Bias in Contextualized Word Embeddings

Sat, 01 Jun 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Idiosyncrasies of the Mandarin Chinese Classifier System

Sat, 01 Jun 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Complexity and Typology of Inflectional Morphological Systems

Fri, 01 Mar 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate

Tue, 01 Jan 2019 00:00:00 +0000

A Discriminative Latent-Variable Model for Bilingual Lexicon Induction

Mon, 01 Oct 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction

Mon, 01 Oct 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Hard Non-Monotonic Attention for Character-Level Transduction

Mon, 01 Oct 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Marrying Universal Dependencies and Universal Morphology

Mon, 01 Oct 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

Mon, 01 Oct 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Structured Variational Autoencoder for Contextual Morphological Inflection

Sun, 01 Jul 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Deep Generative Model of Vowel Formant Typology

Fri, 01 Jun 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Are All Languages Equally Hard to Language-Model?

Fri, 01 Jun 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Unsupervised Disambiguation of Syncretism in Inflected Lexicons

Fri, 01 Jun 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

UniMorph 2.0: Universal Morphology

Tue, 01 May 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Explaining and Generalizing Back-Translation through Wake-Sleep

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Joint Semantic Synthesis and Morphological Analysis of the Derived Word

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On the Diachronic Stability of Irregularity in Inflectional Morphology

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Low-Resource Named Entity Recognition with Cross-lingual, Character-Level Neural Conditional Random Fields

Wed, 01 Nov 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Cross-lingual, Character-Level Neural Morphological Tagging

Fri, 01 Sep 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Paradigm Completion for Derivational Morphology

Fri, 01 Sep 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

CoNLL--SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages

Tue, 01 Aug 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles

Tue, 01 Aug 2017 00:00:00 +0000

Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles

Tue, 01 Aug 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

One-Shot Neural Cross-Lingual Transfer for Paradigm Completion

Tue, 01 Aug 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Probabilistic Typology: Deep Generative Models of Vowel Inventories

Tue, 01 Aug 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax

Sat, 01 Apr 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Context-Aware Prediction of Derivational Word-forms

Sat, 01 Apr 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis

Sat, 01 Apr 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Morphological Analysis of the Dravidian Language Family

Sat, 01 Apr 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion

Sat, 01 Apr 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Neural Multi-Source Morphological Reinflection

Sat, 01 Apr 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Morphological Segmentation Inside-Out

Tue, 01 Nov 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Neural Morphological Analysis: Encoding-Decoding Canonical Segments

Tue, 01 Nov 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity

Tue, 01 Nov 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Morphological Smoothing and Extrapolation of Word Embeddings

Mon, 01 Aug 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

The SIGMORPHON 2016 Shared Task—Morphological Reinflection

Mon, 01 Aug 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Joint Model of Orthography and Morphological Segmentation

Wed, 01 Jun 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Weighting Finite-State Transductions With Neural Context

Wed, 01 Jun 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Analysis of Morphology in Topic Modeling

Fri, 01 Jan 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Contrastive Morphological Typology and Logical Hierarchies

Fri, 01 Jan 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Dual Decomposition Inference for Graphical Models over Strings

Tue, 01 Sep 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Joint Lemmatization and Morphological Tagging with Lemming

Tue, 01 Sep 2015 00:00:00 +0000

Joint Lemmatization and Morphological Tagging with Lemming

Tue, 01 Sep 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Labeled Morphological Segmentation with Semi-Markov Models

Wed, 01 Jul 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Morphological Word Embeddings

Wed, 01 Jul 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Penalized Expectation Propagation for Graphical Models over Strings

Wed, 01 Jul 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Modeling Word Forms Using Latent Underlying Morphs and Phonology

Thu, 01 Jan 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Stochastic Contextual Edit Distance and Probabilistic FSTs

Sun, 01 Jun 2014 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Multi-Dialect, Multi-Genre Corpus of Informal Written Arabic

Wed, 01 Jan 2014 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

An Algerian Arabic-French Code-Switched Corpus

Wed, 01 Jan 2014 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Translation of the CALLHOME Egyptian Arabic Corpus For Conversational Speech Translation

Wed, 01 Jan 2014 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Advanced Formal Language Theory, Spring 2022

Mon, 01 Jan 0001 00:00:00 +0000

Advanced Formal Language Theory, Spring 2023

Mon, 01 Jan 0001 00:00:00 +0000

Advanced Formal Language Theory, Spring 2024

Mon, 01 Jan 0001 00:00:00 +0000

Advanced Formal Language Theory, Spring 2025

Mon, 01 Jan 0001 00:00:00 +0000

Advanced Formal Language Theory, Spring 2026

Mon, 01 Jan 0001 00:00:00 +0000

COLING 2022

Mon, 01 Jan 0001 00:00:00 +0000

Dependency Structures and Lexicalized Grammars

Mon, 01 Jan 0001 00:00:00 +0000

ESSLLI 2021

Mon, 01 Jan 0001 00:00:00 +0000

Formal Language Theory and Neural Networks

Mon, 01 Jan 0001 00:00:00 +0000

Generating Text from Language Models

Mon, 01 Jan 0001 00:00:00 +0000

Large Language Models, Spring 2023

Mon, 01 Jan 0001 00:00:00 +0000

Large Language Models, Spring 2024

Mon, 01 Jan 0001 00:00:00 +0000

Large Language Models, Spring 2025

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Autumn 2020

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Fall 2021

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Fall 2022

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Fall 2023

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Fall 2024

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Fall 2025

Mon, 01 Jan 0001 00:00:00 +0000

Natural Language Processing, Spring 2021

Mon, 01 Jan 0001 00:00:00 +0000

Neural Networks and Computational Complexity, Fall 2024

Mon, 01 Jan 0001 00:00:00 +0000

NLP in the Wild, Spring 2024

Mon, 01 Jan 0001 00:00:00 +0000

Philosophy of Language and Computation I, Spring 2024

Mon, 01 Jan 0001 00:00:00 +0000

Philosophy of Language and Computation I, Spring 2026

Mon, 01 Jan 0001 00:00:00 +0000

Philosophy of Language and Computation II, Spring 2023

Mon, 01 Jan 0001 00:00:00 +0000

Philosophy of Language and Computation II, Spring 2025

Mon, 01 Jan 0001 00:00:00 +0000

Philosophy of Language and Computation, Autumn 2022

Mon, 01 Jan 0001 00:00:00 +0000

Understanding Context-Free Parsing Algorithms

Mon, 01 Jan 0001 00:00:00 +0000