@inproceedings{charlet-etal-2020-cross,
title = "Cross-lingual and Cross-domain Evaluation of Machine Reading Comprehension with Squad and {CALOR}-Quest Corpora",
author = "Charlet, Delphine and
Damnati, Geraldine and
Bechet, Frederic and
Marzinotto, Gabriel and
Heinecke, Johannes",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.674/",
pages = "5491--5497",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Machine Reading received recently a lot of attention thanks to both the availability of very large corpora such as SQuAD or MS MARCO containing triplets (document, question, answer), and the introduction of Transformer Language Models such as BERT which obtain excellent results, even matching human performance according to the SQuAD leaderboard. One of the key features of Transformer Models is their ability to be jointly trained across multiple languages, using a shared subword vocabulary, leading to the construction of cross-lingual lexical representations. This feature has been used recently to perform zero-shot cross-lingual experiments where a multilingual BERT model fine-tuned on a machine reading comprehension task exclusively for English was directly applied to Chinese and French documents with interesting performance. In this paper we study the cross-language and cross-domain capabilities of BERT on a Machine Reading Comprehension task on two corpora: SQuAD and a new French Machine Reading dataset, called CALOR-QUEST. The semantic annotation available on CALOR-QUEST allows us to give a detailed analysis on the kinds of questions that are properly handled through the cross-language process. We will try to answer this question: which factor between language mismatch and domain mismatch has the strongest influence on the performances of a Machine Reading Comprehension task?"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="charlet-etal-2020-cross">
<titleInfo>
<title>Cross-lingual and Cross-domain Evaluation of Machine Reading Comprehension with Squad and CALOR-Quest Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Delphine</namePart>
<namePart type="family">Charlet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geraldine</namePart>
<namePart type="family">Damnati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Marzinotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Heinecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Machine Reading received recently a lot of attention thanks to both the availability of very large corpora such as SQuAD or MS MARCO containing triplets (document, question, answer), and the introduction of Transformer Language Models such as BERT which obtain excellent results, even matching human performance according to the SQuAD leaderboard. One of the key features of Transformer Models is their ability to be jointly trained across multiple languages, using a shared subword vocabulary, leading to the construction of cross-lingual lexical representations. This feature has been used recently to perform zero-shot cross-lingual experiments where a multilingual BERT model fine-tuned on a machine reading comprehension task exclusively for English was directly applied to Chinese and French documents with interesting performance. In this paper we study the cross-language and cross-domain capabilities of BERT on a Machine Reading Comprehension task on two corpora: SQuAD and a new French Machine Reading dataset, called CALOR-QUEST. The semantic annotation available on CALOR-QUEST allows us to give a detailed analysis on the kinds of questions that are properly handled through the cross-language process. We will try to answer this question: which factor between language mismatch and domain mismatch has the strongest influence on the performances of a Machine Reading Comprehension task?</abstract>
<identifier type="citekey">charlet-etal-2020-cross</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.674/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5491</start>
<end>5497</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual and Cross-domain Evaluation of Machine Reading Comprehension with Squad and CALOR-Quest Corpora
%A Charlet, Delphine
%A Damnati, Geraldine
%A Bechet, Frederic
%A Marzinotto, Gabriel
%A Heinecke, Johannes
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F charlet-etal-2020-cross
%X Machine Reading received recently a lot of attention thanks to both the availability of very large corpora such as SQuAD or MS MARCO containing triplets (document, question, answer), and the introduction of Transformer Language Models such as BERT which obtain excellent results, even matching human performance according to the SQuAD leaderboard. One of the key features of Transformer Models is their ability to be jointly trained across multiple languages, using a shared subword vocabulary, leading to the construction of cross-lingual lexical representations. This feature has been used recently to perform zero-shot cross-lingual experiments where a multilingual BERT model fine-tuned on a machine reading comprehension task exclusively for English was directly applied to Chinese and French documents with interesting performance. In this paper we study the cross-language and cross-domain capabilities of BERT on a Machine Reading Comprehension task on two corpora: SQuAD and a new French Machine Reading dataset, called CALOR-QUEST. The semantic annotation available on CALOR-QUEST allows us to give a detailed analysis on the kinds of questions that are properly handled through the cross-language process. We will try to answer this question: which factor between language mismatch and domain mismatch has the strongest influence on the performances of a Machine Reading Comprehension task?
%U https://aclanthology.org/2020.lrec-1.674/
%P 5491-5497
Markdown (Informal)
[Cross-lingual and Cross-domain Evaluation of Machine Reading Comprehension with Squad and CALOR-Quest Corpora](https://aclanthology.org/2020.lrec-1.674/) (Charlet et al., LREC 2020)
ACL