Pinned Repositories
rethinking-demonstrations
DPR
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
MetaICL
An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi
NPM
The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)
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
Channel-LM-Prompting
An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"
DecompRC
An original implementation of ACL 2019, "Multi-hop Reading Comprehension through Question Decomposition and Rescoring"
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"
qa-hard-em
An original implementation of EMNLP 2019, "A Discrete Hard EM Approach for Weakly Supervised Question Answering"
shmsw25's Repositories
shmsw25/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"
shmsw25/DecompRC
An original implementation of ACL 2019, "Multi-hop Reading Comprehension through Question Decomposition and Rescoring"
shmsw25/qa-hard-em
An original implementation of EMNLP 2019, "A Discrete Hard EM Approach for Weakly Supervised Question Answering"
shmsw25/Channel-LM-Prompting
An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"
shmsw25/bart-closed-book-qa
A BART version of an open-domain QA model in a closed-book setup
shmsw25/AmbigQA
An original implementation of EMNLP 2020, "AmbigQA: Answering Ambiguous Open-domain Questions"
shmsw25/qa-transfer
An original implementation of ACL 2017, "Question Answering through Transfer Learning from Large Fine-grained Supervision Data"
shmsw25/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)
shmsw25/GraphRetriever
GraphRetriever in the paper "Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering"
shmsw25/naacl2021-longdoc-tutorial
shmsw25/MetaICL
An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi
shmsw25/BeautifulSoup4
git mirror for Beautiful Soup 4.3.2
shmsw25/faviq
FaVIQ: Fact Verification from Information-seeking Questions
shmsw25/faviq.github.io
shmsw25/OptiPrompt
NAACL'2021: Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240
shmsw25/qrn
Query Reduction Networks