A game theoretic approach to explain the output of any machine learning model.

ACL2023 - AlignScore, a metric for factual consistency evaluation.

Source Code of Paper "GPTScore: Evaluate as You Desire"

Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings (EMNLP 2022 paper)

An explainable sentence similarity measurement

EMNLP accepted paper

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

Python packaging and dependency management made easy

End-to-end neural table-text understanding models.

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Shared code for training sentence embeddings with Flax / JAX

95.47% on CIFAR10 with PyTorch

Transformers for Longer Sequences

Long Range Arena for Benchmarking Efficient Transformers

Code for "High-Precision Model-Agnostic Explanations" paper

Code for the ACL 2020 paper 'tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection'.

Faithfulness and factuality annotations of XSum summaries from our paper "On Faithfulness and Factuality in Abstractive Summarization" (https://www.aclweb.org/anthology/2020.acl-main.173.pdf).

Question Answering and Generation for Summarization

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

LongSumm - Scientific Document Summarization Task

Human-free quality estimation of document summaries

CoLing 2020 Paper Vec2Sent: Probing Sentence Embeddings with Natural Language Generation

Multilingual abstractive summarization dataset extracted from WikiHow.

Lime: Explaining the predictions of any machine learning classifier