@inproceedings{zhu-etal-2020-question,
title = "Question Answering with Long Multiple-Span Answers",
author = "Zhu, Ming and
Ahuja, Aman and
Juan, Da-Cheng and
Wei, Wei and
Reddy, Chandan K.",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.342/",
doi = "10.18653/v1/2020.findings-emnlp.342",
pages = "3840--3849",
abstract = "Answering questions in many real-world applications often requires complex and precise information excerpted from texts spanned across a long document. However, currently no such annotated dataset is publicly available, which hinders the development of neural question-answering (QA) systems. To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document. We also propose MultiCo, a neural architecture that is able to capture the relevance among multiple answer spans, by using a query-based contextualized sentence selection approach, for forming the answer to the given question. We also demonstrate that conventional QA models are not suitable for this type of task and perform poorly in this setting. Extensive experiments are conducted, and the experimental results confirm the proposed model significantly outperforms the state-of-the-art QA models in this multi-span QA setting."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2020-question">
<titleInfo>
<title>Question Answering with Long Multiple-Span Answers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Ahuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Da-Cheng</namePart>
<namePart type="family">Juan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandan</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Answering questions in many real-world applications often requires complex and precise information excerpted from texts spanned across a long document. However, currently no such annotated dataset is publicly available, which hinders the development of neural question-answering (QA) systems. To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document. We also propose MultiCo, a neural architecture that is able to capture the relevance among multiple answer spans, by using a query-based contextualized sentence selection approach, for forming the answer to the given question. We also demonstrate that conventional QA models are not suitable for this type of task and perform poorly in this setting. Extensive experiments are conducted, and the experimental results confirm the proposed model significantly outperforms the state-of-the-art QA models in this multi-span QA setting.</abstract>
<identifier type="citekey">zhu-etal-2020-question</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.342</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.342/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3840</start>
<end>3849</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Question Answering with Long Multiple-Span Answers
%A Zhu, Ming
%A Ahuja, Aman
%A Juan, Da-Cheng
%A Wei, Wei
%A Reddy, Chandan K.
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zhu-etal-2020-question
%X Answering questions in many real-world applications often requires complex and precise information excerpted from texts spanned across a long document. However, currently no such annotated dataset is publicly available, which hinders the development of neural question-answering (QA) systems. To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document. We also propose MultiCo, a neural architecture that is able to capture the relevance among multiple answer spans, by using a query-based contextualized sentence selection approach, for forming the answer to the given question. We also demonstrate that conventional QA models are not suitable for this type of task and perform poorly in this setting. Extensive experiments are conducted, and the experimental results confirm the proposed model significantly outperforms the state-of-the-art QA models in this multi-span QA setting.
%R 10.18653/v1/2020.findings-emnlp.342
%U https://aclanthology.org/2020.findings-emnlp.342/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.342
%P 3840-3849
Markdown (Informal)
[Question Answering with Long Multiple-Span Answers](https://aclanthology.org/2020.findings-emnlp.342/) (Zhu et al., Findings 2020)
ACL
- Ming Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei, and Chandan K. Reddy. 2020. Question Answering with Long Multiple-Span Answers. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3840–3849, Online. Association for Computational Linguistics.