@inproceedings{wang-etal-2021-sentence-hood,
title = "What If Sentence-hood is Hard to Define: A Case Study in {C}hinese Reading Comprehension",
author = "Wang, Jiawei and
Zhao, Hai and
Zhao, Yinggong and
Shen, Libin",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.202",
doi = "10.18653/v1/2021.findings-emnlp.202",
pages = "2348--2359",
abstract = "Machine reading comprehension (MRC) is a challenging NLP task for it requires to carefully deal with all linguistic granularities from word, sentence to passage. For extractive MRC, the answer span has been shown mostly determined by key evidence linguistic units, in which it is a sentence in most cases. However, we recently discovered that sentences may not be clearly defined in many languages to different extents, so that this causes so-called location unit ambiguity problem and as a result makes it difficult for the model to determine which sentence exactly contains the answer span when sentence itself has not been clearly defined at all. Taking Chinese language as a case study, we explain and analyze such a linguistic phenomenon and correspondingly propose a reader with Explicit Span-Sentence Predication to alleviate such a problem. Our proposed reader eventually helps achieve a new state-of-the-art on Chinese MRC benchmark and shows great potential in dealing with other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-sentence-hood">
<titleInfo>
<title>What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinggong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libin</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine reading comprehension (MRC) is a challenging NLP task for it requires to carefully deal with all linguistic granularities from word, sentence to passage. For extractive MRC, the answer span has been shown mostly determined by key evidence linguistic units, in which it is a sentence in most cases. However, we recently discovered that sentences may not be clearly defined in many languages to different extents, so that this causes so-called location unit ambiguity problem and as a result makes it difficult for the model to determine which sentence exactly contains the answer span when sentence itself has not been clearly defined at all. Taking Chinese language as a case study, we explain and analyze such a linguistic phenomenon and correspondingly propose a reader with Explicit Span-Sentence Predication to alleviate such a problem. Our proposed reader eventually helps achieve a new state-of-the-art on Chinese MRC benchmark and shows great potential in dealing with other languages.</abstract>
<identifier type="citekey">wang-etal-2021-sentence-hood</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.202</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.202</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2348</start>
<end>2359</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension
%A Wang, Jiawei
%A Zhao, Hai
%A Zhao, Yinggong
%A Shen, Libin
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F wang-etal-2021-sentence-hood
%X Machine reading comprehension (MRC) is a challenging NLP task for it requires to carefully deal with all linguistic granularities from word, sentence to passage. For extractive MRC, the answer span has been shown mostly determined by key evidence linguistic units, in which it is a sentence in most cases. However, we recently discovered that sentences may not be clearly defined in many languages to different extents, so that this causes so-called location unit ambiguity problem and as a result makes it difficult for the model to determine which sentence exactly contains the answer span when sentence itself has not been clearly defined at all. Taking Chinese language as a case study, we explain and analyze such a linguistic phenomenon and correspondingly propose a reader with Explicit Span-Sentence Predication to alleviate such a problem. Our proposed reader eventually helps achieve a new state-of-the-art on Chinese MRC benchmark and shows great potential in dealing with other languages.
%R 10.18653/v1/2021.findings-emnlp.202
%U https://aclanthology.org/2021.findings-emnlp.202
%U https://doi.org/10.18653/v1/2021.findings-emnlp.202
%P 2348-2359
Markdown (Informal)
[What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension](https://aclanthology.org/2021.findings-emnlp.202) (Wang et al., Findings 2021)
ACL