Stars
Implementation of the EMNLP 2025 Main (Oral) paper "Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation"
Dataset and Implementation of the EMNLP 2025 SAC Highlights paper "LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference"
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A beautiful, simple, clean, and responsive Jekyll theme for academics
Code to probe Natural Language Generation (NLG) systems for their uncertainty, and to evaluate it against human production variability (i.e., aleatoric uncertainty)
Implementation of the EMNLP 2024 paper - "Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?; and the ACL 2025 paper - A Rose by An…
Official style files for papers submitted to venues of the Association for Computational Linguistics
[EMNLP 2023] Can Large Language Models Capture Dissenting Human Voices?
Distance correlation and related E-statistics in Python
Code accompanying the EMNLP 2022 paper "Stop Measuring Calibration When Humans Disagree" in which we show problems with popular calibration metrics like ECE in settings where more than one answer i…
Chat Templates for 🤗 HuggingFace Large Language Models
A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, accompanying The 'Problem' of Human Label Variation: On Grou…
ICCV2023 paper on Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization
UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specific adaptation. This repository includes the code for "UDapter…
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
[EMNLP 2022 main conference] Wider & Closer: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition
Winner system (USTC-NELSLIP) of SemEval 2022 MultiCoNER shared task on 3 tracks (Chinese, Bangla, Code-Mixed).
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Code of our paper Multi-Level Contrastive Learning for Cross-Lingual Alignment in ICASSP 2022
Must-read papers on prompt-based tuning for pre-trained language models.
Compendium of the resources available from top NLP conferences.