@inproceedings{li-etal-2022-museclir,
title = "{M}u{S}e{CLIR}: A Multiple Senses and Cross-lingual Information Retrieval Dataset",
author = "Li, Wing Yan and
Weeds, Julie and
Weir, David",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.96",
pages = "1128--1135",
abstract = "This paper addresses a deficiency in existing cross-lingual information retrieval (CLIR) datasets and provides a robust evaluation of CLIR systems{'} disambiguation ability. CLIR is commonly tackled by combining translation and traditional IR. Due to translation ambiguity, the problem of ambiguity is worse in CLIR than in monolingual IR. But existing auto-generated CLIR datasets are dominated by searches for named entity mentions, which does not provide a good measure for disambiguation performance, as named entity mentions can often be transliterated across languages and tend not to have multiple translations. Therefore, we introduce a new evaluation dataset (MuSeCLIR) to address this inadequacy. The dataset focusses on polysemous common nouns with multiple possible translations. MuSeCLIR is constructed from multilingual Wikipedia and supports searches on documents written in European (French, German, Italian) and Asian (Chinese, Japanese) languages. We provide baseline statistical and neural model results on MuSeCLIR which show that MuSeCLIR has a higher requirement on the ability of systems to disambiguate query terms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-museclir">
<titleInfo>
<title>MuSeCLIR: A Multiple Senses and Cross-lingual Information Retrieval Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wing</namePart>
<namePart type="given">Yan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Weeds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Weir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper addresses a deficiency in existing cross-lingual information retrieval (CLIR) datasets and provides a robust evaluation of CLIR systems’ disambiguation ability. CLIR is commonly tackled by combining translation and traditional IR. Due to translation ambiguity, the problem of ambiguity is worse in CLIR than in monolingual IR. But existing auto-generated CLIR datasets are dominated by searches for named entity mentions, which does not provide a good measure for disambiguation performance, as named entity mentions can often be transliterated across languages and tend not to have multiple translations. Therefore, we introduce a new evaluation dataset (MuSeCLIR) to address this inadequacy. The dataset focusses on polysemous common nouns with multiple possible translations. MuSeCLIR is constructed from multilingual Wikipedia and supports searches on documents written in European (French, German, Italian) and Asian (Chinese, Japanese) languages. We provide baseline statistical and neural model results on MuSeCLIR which show that MuSeCLIR has a higher requirement on the ability of systems to disambiguate query terms.</abstract>
<identifier type="citekey">li-etal-2022-museclir</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.96</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1128</start>
<end>1135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuSeCLIR: A Multiple Senses and Cross-lingual Information Retrieval Dataset
%A Li, Wing Yan
%A Weeds, Julie
%A Weir, David
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F li-etal-2022-museclir
%X This paper addresses a deficiency in existing cross-lingual information retrieval (CLIR) datasets and provides a robust evaluation of CLIR systems’ disambiguation ability. CLIR is commonly tackled by combining translation and traditional IR. Due to translation ambiguity, the problem of ambiguity is worse in CLIR than in monolingual IR. But existing auto-generated CLIR datasets are dominated by searches for named entity mentions, which does not provide a good measure for disambiguation performance, as named entity mentions can often be transliterated across languages and tend not to have multiple translations. Therefore, we introduce a new evaluation dataset (MuSeCLIR) to address this inadequacy. The dataset focusses on polysemous common nouns with multiple possible translations. MuSeCLIR is constructed from multilingual Wikipedia and supports searches on documents written in European (French, German, Italian) and Asian (Chinese, Japanese) languages. We provide baseline statistical and neural model results on MuSeCLIR which show that MuSeCLIR has a higher requirement on the ability of systems to disambiguate query terms.
%U https://aclanthology.org/2022.coling-1.96
%P 1128-1135
Markdown (Informal)
[MuSeCLIR: A Multiple Senses and Cross-lingual Information Retrieval Dataset](https://aclanthology.org/2022.coling-1.96) (Li et al., COLING 2022)
ACL