@inproceedings{su-etal-2023-context,
title = "Context Generation Improves Open Domain Question Answering",
author = "Su, Dan and
Patwary, Mostofa and
Prabhumoye, Shrimai and
Xu, Peng and
Prenger, Ryan and
Shoeybi, Mohammad and
Fung, Pascale and
Anandkumar, Anima and
Catanzaro, Bryan",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.60",
doi = "10.18653/v1/2023.findings-eacl.60",
pages = "793--808",
abstract = "Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to leverage the stored knowledge. However, they do not fully exploit the parameterized knowledge. To address this inefficiency, we propose a two-stage, closed-book QA framework which employs a coarse-to-fine approach to extract the relevant knowledge and answer a question. We first generate a related context for a given question by prompting a pretrained LM. We then prompt the same LM to generate an answer using the generated context and the question. Additionally, we marginalize over the generated contexts to improve the accuracies and reduce context uncertainty. Experimental results on three QA benchmarks show that our method significantly outperforms previous closed-book QA methods. For example on TriviaQA, our method improves exact match accuracy from 55.3{\%} to 68.6{\%}, and is on par with open-book QA methods (68.6{\%} vs. 68.0{\%}). Our results show that our new methodology is able to better exploit the stored knowledge in pretrained LMs without adding extra learnable parameters or needing finetuning, and paves the way for hybrid models that integrate pretrained LMs with external knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-etal-2023-context">
<titleInfo>
<title>Context Generation Improves Open Domain Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostofa</namePart>
<namePart type="family">Patwary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrimai</namePart>
<namePart type="family">Prabhumoye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Prenger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Shoeybi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anima</namePart>
<namePart type="family">Anandkumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Catanzaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to leverage the stored knowledge. However, they do not fully exploit the parameterized knowledge. To address this inefficiency, we propose a two-stage, closed-book QA framework which employs a coarse-to-fine approach to extract the relevant knowledge and answer a question. We first generate a related context for a given question by prompting a pretrained LM. We then prompt the same LM to generate an answer using the generated context and the question. Additionally, we marginalize over the generated contexts to improve the accuracies and reduce context uncertainty. Experimental results on three QA benchmarks show that our method significantly outperforms previous closed-book QA methods. For example on TriviaQA, our method improves exact match accuracy from 55.3% to 68.6%, and is on par with open-book QA methods (68.6% vs. 68.0%). Our results show that our new methodology is able to better exploit the stored knowledge in pretrained LMs without adding extra learnable parameters or needing finetuning, and paves the way for hybrid models that integrate pretrained LMs with external knowledge.</abstract>
<identifier type="citekey">su-etal-2023-context</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.60</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.60</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>793</start>
<end>808</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context Generation Improves Open Domain Question Answering
%A Su, Dan
%A Patwary, Mostofa
%A Prabhumoye, Shrimai
%A Xu, Peng
%A Prenger, Ryan
%A Shoeybi, Mohammad
%A Fung, Pascale
%A Anandkumar, Anima
%A Catanzaro, Bryan
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F su-etal-2023-context
%X Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to leverage the stored knowledge. However, they do not fully exploit the parameterized knowledge. To address this inefficiency, we propose a two-stage, closed-book QA framework which employs a coarse-to-fine approach to extract the relevant knowledge and answer a question. We first generate a related context for a given question by prompting a pretrained LM. We then prompt the same LM to generate an answer using the generated context and the question. Additionally, we marginalize over the generated contexts to improve the accuracies and reduce context uncertainty. Experimental results on three QA benchmarks show that our method significantly outperforms previous closed-book QA methods. For example on TriviaQA, our method improves exact match accuracy from 55.3% to 68.6%, and is on par with open-book QA methods (68.6% vs. 68.0%). Our results show that our new methodology is able to better exploit the stored knowledge in pretrained LMs without adding extra learnable parameters or needing finetuning, and paves the way for hybrid models that integrate pretrained LMs with external knowledge.
%R 10.18653/v1/2023.findings-eacl.60
%U https://aclanthology.org/2023.findings-eacl.60
%U https://doi.org/10.18653/v1/2023.findings-eacl.60
%P 793-808
Markdown (Informal)
[Context Generation Improves Open Domain Question Answering](https://aclanthology.org/2023.findings-eacl.60) (Su et al., Findings 2023)
ACL
- Dan Su, Mostofa Patwary, Shrimai Prabhumoye, Peng Xu, Ryan Prenger, Mohammad Shoeybi, Pascale Fung, Anima Anandkumar, and Bryan Catanzaro. 2023. Context Generation Improves Open Domain Question Answering. In Findings of the Association for Computational Linguistics: EACL 2023, pages 793–808, Dubrovnik, Croatia. Association for Computational Linguistics.