Sewon Min

FActScore. A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

DecompRC. An original implementation of ACL 2019, "Multi-hop Reading Comprehension through Question Decomposition and Rescoring"

qa-hard-em. An original implementation of EMNLP 2019, "A Discrete Hard EM Approach for Weakly Supervised Question Answering"

Channel-LM-Prompting. An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"

AmbigQA. An original implementation of EMNLP 2020, "AmbigQA: Answering Ambiguous Open-domain Questions"

bart-closed-book-qa. A BART version of an open-domain QA model in a closed-book setup

qa-transfer. An original implementation of ACL 2017, "Question Answering through Transfer Learning from Large Fine-grained Supervision Data"

single-hop-rc. An original implementation of ACL 2019, "Compositional Questions Do Not Necessitate Multi-hop Reasoning" (Single-hop Reading Comprehension Model based on BERT)

GraphRetriever. GraphRetriever in the paper "Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering"

naacl2021-longdoc-tutorial. Python

MetaICL. An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi

retrieval-scaling. Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".