@inproceedings{zhao-etal-2021-multi-step,
title = "Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval",
author = "Zhao, Chen and
Xiong, Chenyan and
Boyd-Graber, Jordan and
Daum{\'e} III, Hal",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.368",
doi = "10.18653/v1/2021.naacl-main.368",
pages = "4635--4641",
abstract = "Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2021-multi-step">
<titleInfo>
<title>Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyan</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hal</namePart>
<namePart type="family">Daumé III</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.</abstract>
<identifier type="citekey">zhao-etal-2021-multi-step</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.368</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.368</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>4635</start>
<end>4641</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
%A Zhao, Chen
%A Xiong, Chenyan
%A Boyd-Graber, Jordan
%A Daumé III, Hal
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F zhao-etal-2021-multi-step
%X Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.
%R 10.18653/v1/2021.naacl-main.368
%U https://aclanthology.org/2021.naacl-main.368
%U https://doi.org/10.18653/v1/2021.naacl-main.368
%P 4635-4641
Markdown (Informal)
[Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval](https://aclanthology.org/2021.naacl-main.368) (Zhao et al., NAACL 2021)
ACL
- Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, and Hal Daumé III. 2021. Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4635–4641, Online. Association for Computational Linguistics.