@inproceedings{de-bruyn-etal-2021-mfaq,
title = "{MFAQ}: a Multilingual {FAQ} Dataset",
author = "De Bruyn, Maxime and
Lotfi, Ehsan and
Buhmann, Jeska and
Daelemans, Walter",
editor = "Fisch, Adam and
Talmor, Alon and
Chen, Danqi and
Choi, Eunsol and
Seo, Minjoon and
Lewis, Patrick and
Jia, Robin and
Min, Sewon",
booktitle = "Proceedings of the 3rd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrqa-1.1",
doi = "10.18653/v1/2021.mrqa-1.1",
pages = "1--13",
abstract = "In this paper, we present the first multilingual FAQ dataset publicly available. We collected around 6M FAQ pairs from the web, in 21 different languages. Although this is significantly larger than existing FAQ retrieval datasets, it comes with its own challenges: duplication of content and uneven distribution of topics. We adopt a similar setup as Dense Passage Retrieval (DPR) and test various bi-encoders on this dataset. Our experiments reveal that a multilingual model based on XLM-RoBERTa achieves the best results, except for English. Lower resources languages seem to learn from one another as a multilingual model achieves a higher MRR than language-specific ones. Our qualitative analysis reveals the brittleness of the model on simple word changes. We publicly release our dataset, model, and training script.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-bruyn-etal-2021-mfaq">
<titleInfo>
<title>MFAQ: a Multilingual FAQ Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">De Bruyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Lotfi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeska</namePart>
<namePart type="family">Buhmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</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>Proceedings of the 3rd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</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>In this paper, we present the first multilingual FAQ dataset publicly available. We collected around 6M FAQ pairs from the web, in 21 different languages. Although this is significantly larger than existing FAQ retrieval datasets, it comes with its own challenges: duplication of content and uneven distribution of topics. We adopt a similar setup as Dense Passage Retrieval (DPR) and test various bi-encoders on this dataset. Our experiments reveal that a multilingual model based on XLM-RoBERTa achieves the best results, except for English. Lower resources languages seem to learn from one another as a multilingual model achieves a higher MRR than language-specific ones. Our qualitative analysis reveals the brittleness of the model on simple word changes. We publicly release our dataset, model, and training script.</abstract>
<identifier type="citekey">de-bruyn-etal-2021-mfaq</identifier>
<identifier type="doi">10.18653/v1/2021.mrqa-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.mrqa-1.1</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MFAQ: a Multilingual FAQ Dataset
%A De Bruyn, Maxime
%A Lotfi, Ehsan
%A Buhmann, Jeska
%A Daelemans, Walter
%Y Fisch, Adam
%Y Talmor, Alon
%Y Chen, Danqi
%Y Choi, Eunsol
%Y Seo, Minjoon
%Y Lewis, Patrick
%Y Jia, Robin
%Y Min, Sewon
%S Proceedings of the 3rd Workshop on Machine Reading for Question Answering
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F de-bruyn-etal-2021-mfaq
%X In this paper, we present the first multilingual FAQ dataset publicly available. We collected around 6M FAQ pairs from the web, in 21 different languages. Although this is significantly larger than existing FAQ retrieval datasets, it comes with its own challenges: duplication of content and uneven distribution of topics. We adopt a similar setup as Dense Passage Retrieval (DPR) and test various bi-encoders on this dataset. Our experiments reveal that a multilingual model based on XLM-RoBERTa achieves the best results, except for English. Lower resources languages seem to learn from one another as a multilingual model achieves a higher MRR than language-specific ones. Our qualitative analysis reveals the brittleness of the model on simple word changes. We publicly release our dataset, model, and training script.
%R 10.18653/v1/2021.mrqa-1.1
%U https://aclanthology.org/2021.mrqa-1.1
%U https://doi.org/10.18653/v1/2021.mrqa-1.1
%P 1-13
Markdown (Informal)
[MFAQ: a Multilingual FAQ Dataset](https://aclanthology.org/2021.mrqa-1.1) (De Bruyn et al., MRQA 2021)
ACL
- Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, and Walter Daelemans. 2021. MFAQ: a Multilingual FAQ Dataset. In Proceedings of the 3rd Workshop on Machine Reading for Question Answering, pages 1–13, Punta Cana, Dominican Republic. Association for Computational Linguistics.