Controlled text generation with programmable constraints

This repository contains code for the paper Direct Preference Optimization with an Offset (ODPO).

This is the repository containing code to replicate the experiments in our EMNLP 2024 paper, "A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors".

Generic PyTorch implementation of einsum that supports different semirings

An extendible and configurable PDF manipulation layer library written in java.

Spectral Probing (EMNLP 2022)

Code Repository for "Please Mind the Root: Decoding Arborescences for Dependency Parsing" and "On Finding the K-best Non-projective Dependency Trees"

Code accompanying paper "The Architectural Bottleneck Principle".

Automatic Generation of Scaffolding Questions for Learning Math, EMNLP 2022

Official implementations for Investigating the Role of Centering Theory in Neural Coreference Resolution

a set of scripts that could be useful in seq2seq pro/post processing

PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction with Language Models, EMNLP 22. https://arxiv.org/pdf/2210.14698.pdf

Source code for "Packed Levitated Marker for Entity and Relation Extraction"

Research code for pixel-based encoders of language (PIXEL)

Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"

A Structured Span Selector (NAACL 2022). A structured span selector with a WCFG for span selection tasks (coreference resolution, semantic role labelling, etc.)

CUDA kernels for context-free parsing

A corpus of Biomedical papers annotated with mentions of UMLS entities.

CUDA kernels for generalized matrix-multiplication in PyTorch

Pytorch implementation of Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Collaboration with Microsoft, AWS, Google, and ETHZürich Analytics Club (2022 Datathon Project)

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Official implementations for (1) BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation and (2) Discourse Centric Evaluation of Machine Translation with a Densely Annotated P…

A PyTorch implementation of the CorefQA Model.