@inproceedings{li-etal-2022-multispanqa,
title = "{M}ulti{S}pan{QA}: A Dataset for Multi-Span Question Answering",
author = "Li, Haonan and
Tomko, Martin and
Vasardani, Maria and
Baldwin, Timothy",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.90/",
doi = "10.18653/v1/2022.naacl-main.90",
pages = "1250--1260",
abstract = "Most existing reading comprehension datasets focus on single-span answers, which can be extracted as a single contiguous span from a given text passage. Multi-span questions, i.e., questions whose answer is a series of multiple discontiguous spans in the text, are common real life but are less studied. In this paper, we present MultiSpanQA, a new dataset that focuses on multi-span questions. Raw questions and contexts are extracted from the Natural Questions dataset. After multi-span re-annotation, MultiSpanQA consists of over a total of 6,000 multi-span questions in the basic version, and over 19,000 examples with unanswerable questions, and questions with single-, and multi-span answers in the expanded version. We introduce new metrics for the purposes of multi-span question answering evaluation, and establish several baselines using advanced models. Finally, we propose a new model which beats all baselines and achieves state-of-the-art on our dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-multispanqa">
<titleInfo>
<title>MultiSpanQA: A Dataset for Multi-Span Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haonan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tomko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Vasardani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most existing reading comprehension datasets focus on single-span answers, which can be extracted as a single contiguous span from a given text passage. Multi-span questions, i.e., questions whose answer is a series of multiple discontiguous spans in the text, are common real life but are less studied. In this paper, we present MultiSpanQA, a new dataset that focuses on multi-span questions. Raw questions and contexts are extracted from the Natural Questions dataset. After multi-span re-annotation, MultiSpanQA consists of over a total of 6,000 multi-span questions in the basic version, and over 19,000 examples with unanswerable questions, and questions with single-, and multi-span answers in the expanded version. We introduce new metrics for the purposes of multi-span question answering evaluation, and establish several baselines using advanced models. Finally, we propose a new model which beats all baselines and achieves state-of-the-art on our dataset.</abstract>
<identifier type="citekey">li-etal-2022-multispanqa</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.90</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.90/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1250</start>
<end>1260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiSpanQA: A Dataset for Multi-Span Question Answering
%A Li, Haonan
%A Tomko, Martin
%A Vasardani, Maria
%A Baldwin, Timothy
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F li-etal-2022-multispanqa
%X Most existing reading comprehension datasets focus on single-span answers, which can be extracted as a single contiguous span from a given text passage. Multi-span questions, i.e., questions whose answer is a series of multiple discontiguous spans in the text, are common real life but are less studied. In this paper, we present MultiSpanQA, a new dataset that focuses on multi-span questions. Raw questions and contexts are extracted from the Natural Questions dataset. After multi-span re-annotation, MultiSpanQA consists of over a total of 6,000 multi-span questions in the basic version, and over 19,000 examples with unanswerable questions, and questions with single-, and multi-span answers in the expanded version. We introduce new metrics for the purposes of multi-span question answering evaluation, and establish several baselines using advanced models. Finally, we propose a new model which beats all baselines and achieves state-of-the-art on our dataset.
%R 10.18653/v1/2022.naacl-main.90
%U https://aclanthology.org/2022.naacl-main.90/
%U https://doi.org/10.18653/v1/2022.naacl-main.90
%P 1250-1260
Markdown (Informal)
[MultiSpanQA: A Dataset for Multi-Span Question Answering](https://aclanthology.org/2022.naacl-main.90/) (Li et al., NAACL 2022)
ACL
- Haonan Li, Martin Tomko, Maria Vasardani, and Timothy Baldwin. 2022. MultiSpanQA: A Dataset for Multi-Span Question Answering. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1250–1260, Seattle, United States. Association for Computational Linguistics.