no code implementations • 17 May 2022 • Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
In this paper, we present a novel attack method FILM for federated learning of language models -- for the first time, we show the feasibility of recovering text from large batch sizes of up to 128 sentences.
1 code implementation • 25 Apr 2022 • Howard Chen, Jacqueline He, Karthik Narasimhan, Danqi Chen
Our experiments reveal that the rationale models show the promise to improve robustness, while they struggle in certain scenarios--when the rationalizer is sensitive to positional bias or lexical choices of attack text.
1 code implementation • ACL 2022 • Mengzhou Xia, Zexuan Zhong, Danqi Chen
The growing size of neural language models has led to increased attention in model compression.
no code implementations • 16 Feb 2022 • Alexander Wettig, Tianyu Gao, Zexuan Zhong, Danqi Chen
Masked language models conventionally use a masking rate of 15% due to the belief that more masking would provide insufficient context to learn good representations, and less masking would make training too expensive.
2 code implementations • ACL 2022 • Huihan Li, Tianyu Gao, Manan Goenka, Danqi Chen
In this work, we conduct the first large-scale human evaluation of state-of-the-art conversational QA systems, where human evaluators converse with models and judge the correctness of their answers.
1 code implementation • EMNLP 2021 • Dan Friedman, Ben Dodge, Danqi Chen
Many datasets have been created for training reading comprehension models, and a natural question is whether we can combine them to build models that (1) perform better on all of the training datasets and (2) generalize and transfer better to new datasets.
1 code implementation • EMNLP 2021 • Christopher Sciavolino, Zexuan Zhong, Jinhyuk Lee, Danqi Chen
Open-domain question answering has exploded in popularity recently due to the success of dense retrieval models, which have surpassed sparse models using only a few supervised training examples.
1 code implementation • EMNLP 2021 • Jinhyuk Lee, Alexander Wettig, Danqi Chen
Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems.
1 code implementation • NAACL 2021 • Howard Chen, Mengzhou Xia, Danqi Chen
One significant challenge in supervised all-words WSD is to classify among senses for a majority of words that lie in the long-tail distribution.
13 code implementations • EMNLP 2021 • Tianyu Gao, Xingcheng Yao, Danqi Chen
This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings.
Ranked #2 on
Semantic Textual Similarity
on SICK
2 code implementations • NAACL 2021 • Zexuan Zhong, Dan Friedman, Danqi Chen
Petroni et al. (2019) demonstrated that it is possible to retrieve world facts from a pre-trained language model by expressing them as cloze-style prompts and interpret the model's prediction accuracy as a lower bound on the amount of factual information it encodes.
no code implementations • 1 Jan 2021 • Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, Hannaneh Hajishirzi, Kenton Lee, Jennimaria Palomaki, Colin Raffel, Adam Roberts, Tom Kwiatkowski, Patrick Lewis, Yuxiang Wu, Heinrich Küttler, Linqing Liu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Sohee Yang, Minjoon Seo, Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Edouard Grave, Ikuya Yamada, Sonse Shimaoka, Masatoshi Suzuki, Shumpei Miyawaki, Shun Sato, Ryo Takahashi, Jun Suzuki, Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz, Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih
We review the EfficientQA competition from NeurIPS 2020.
5 code implementations • ACL 2021 • Tianyu Gao, Adam Fisch, Danqi Chen
We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples.
4 code implementations • ACL 2021 • Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, Danqi Chen
Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019).
Ranked #1 on
Question Answering
on Natural Questions (long)
2 code implementations • NAACL 2021 • Zexuan Zhong, Danqi Chen
Our approach essentially builds on two independent encoders and merely uses the entity model to construct the input for the relation model.
Ranked #1 on
Named Entity Recognition
on ACE 2005
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Yangsibo Huang, Zhao Song, Danqi Chen, Kai Li, Sanjeev Arora
In addition, TextHide fits well with the popular framework of fine-tuning pre-trained language models (e. g., BERT) for any sentence or sentence-pair task.
no code implementations • ACL 2020 • Danqi Chen, Wen-tau Yih
This tutorial provides a comprehensive and coherent overview of cutting-edge research in open-domain question answering (QA), the task of answering questions using a large collection of documents of diversified topics.
12 code implementations • EMNLP 2020 • Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih
Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method.
Ranked #1 on
Question Answering
on SQuAD
7 code implementations • 10 Nov 2019 • Sewon Min, Danqi Chen, Luke Zettlemoyer, Hannaneh Hajishirzi
We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article.
1 code implementation • WS 2019 • Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, Danqi Chen
We present the results of the Machine Reading for Question Answering (MRQA) 2019 shared task on evaluating the generalization capabilities of reading comprehension systems.
1 code implementation • IJCNLP 2019 • Sewon Min, Danqi Chen, Hannaneh Hajishirzi, Luke Zettlemoyer
Many question answering (QA) tasks only provide weak supervision for how the answer should be computed.
Ranked #2 on
Question Answering
on NarrativeQA
47 code implementations • 26 Jul 2019 • Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov
Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.
Ranked #2 on
Common Sense Reasoning
on SWAG
5 code implementations • TACL 2020 • Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, Omer Levy
We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text.
Ranked #1 on
Open-Domain Question Answering
on SearchQA
(F1 metric)
3 code implementations • TACL 2019 • Siva Reddy, Danqi Chen, Christopher D. Manning
Humans gather information by engaging in conversations involving a series of interconnected questions and answers.
Ranked #3 on
Generative Question Answering
on CoQA
Conversational Question Answering
Generative Question Answering
+1
2 code implementations • EMNLP 2017 • Yuhao Zhang, Victor Zhong, Danqi Chen, Gabor Angeli, Christopher D. Manning
The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance.
Ranked #6 on
Relation Extraction
on Re-TACRED
9 code implementations • ACL 2017 • Danqi Chen, Adam Fisch, Jason Weston, Antoine Bordes
This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article.
Ranked #1 on
Open-Domain Question Answering
on SQuAD1.1
3 code implementations • ACL 2016 • Danqi Chen, Jason Bolton, Christopher D. Manning
Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved goal of NLP.
Ranked #3 on
Question Answering
on CNN / Daily Mail
no code implementations • NeurIPS 2013 • Richard Socher, Danqi Chen, Christopher D. Manning, Andrew Ng
We assess the model by considering the problem of predicting additional true relations between entities given a partial knowledge base.