@inproceedings{das-etal-2019-multi,
title = "Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering",
author = "Das, Rajarshi and
Godbole, Ameya and
Kavarthapu, Dilip and
Gong, Zhiyu and
Singhal, Abhishek and
Yu, Mo and
Guo, Xiaoxiao and
Gao, Tian and
Zamani, Hamed and
Zaheer, Manzil and
McCallum, Andrew",
booktitle = "Proceedings of the 2nd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5816",
doi = "10.18653/v1/D19-5816",
pages = "113--118",
abstract = "Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \textit{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to {`}\textit{hop}{'} to other relevant evidence. In a setting, with more than \textbf{5 million} Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by \textbf{10.59} F1.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2019-multi">
<titleInfo>
<title>Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajarshi</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ameya</namePart>
<namePart type="family">Godbole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilip</namePart>
<namePart type="family">Kavarthapu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyu</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxiao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamed</namePart>
<namePart type="family">Zamani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manzil</namePart>
<namePart type="family">Zaheer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to ‘hop’ to other relevant evidence. In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by 10.59 F1.</abstract>
<identifier type="citekey">das-etal-2019-multi</identifier>
<identifier type="doi">10.18653/v1/D19-5816</identifier>
<location>
<url>https://aclanthology.org/D19-5816</url>
</location>
<part>
<date>2019-nov</date>
<extent unit="page">
<start>113</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
%A Das, Rajarshi
%A Godbole, Ameya
%A Kavarthapu, Dilip
%A Gong, Zhiyu
%A Singhal, Abhishek
%A Yu, Mo
%A Guo, Xiaoxiao
%A Gao, Tian
%A Zamani, Hamed
%A Zaheer, Manzil
%A McCallum, Andrew
%S Proceedings of the 2nd Workshop on Machine Reading for Question Answering
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F das-etal-2019-multi
%X Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to ‘hop’ to other relevant evidence. In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by 10.59 F1.
%R 10.18653/v1/D19-5816
%U https://aclanthology.org/D19-5816
%U https://doi.org/10.18653/v1/D19-5816
%P 113-118
Markdown (Informal)
[Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering](https://aclanthology.org/D19-5816) (Das et al., EMNLP 2019)
ACL
- Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, and Andrew McCallum. 2019. Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 113–118, Hong Kong, China. Association for Computational Linguistics.