@inproceedings{goncalo-oliveira-etal-2020-aia,
title = "{AIA}-{BDE}: A Corpus of {FAQ}s in {P}ortuguese and their Variations",
author = "Gon{\c{c}}alo Oliveira, Hugo and
Ferreira, Jo{\~a}o and
Santos, Jos{\'e} and
Fialho, Pedro and
Rodrigues, Ricardo and
Coheur, Luisa and
Alves, Ana",
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-1.669",
pages = "5442--5449",
abstract = "We present AIA-BDE, a corpus of 380 domain-oriented FAQs in Portuguese and their variations, i.e., paraphrases or entailed questions, created manually, by humans, or automatically, with Google Translate. Its aims to be used as a benchmark for FAQ retrieval and automatic question-answering, but may be useful in other contexts, such as the development of task-oriented dialogue systems, or models for natural language inference in an interrogative context. We also report on two experiments. Matching variations with their original questions was not trivial with a set of unsupervised baselines, especially for manually created variations. Besides high performances obtained with ELMo and BERT embeddings, an Information Retrieval system was surprisingly competitive when considering only the first hit. In the second experiment, text classifiers were trained with the original questions, and tested when assigning each variation to one of three possible sources, or assigning them as out-of-domain. Here, the difference between manual and automatic variations was not so significant.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goncalo-oliveira-etal-2020-aia">
<titleInfo>
<title>AIA-BDE: A Corpus of FAQs in Portuguese and their Variations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Gonçalo Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Fialho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">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>We present AIA-BDE, a corpus of 380 domain-oriented FAQs in Portuguese and their variations, i.e., paraphrases or entailed questions, created manually, by humans, or automatically, with Google Translate. Its aims to be used as a benchmark for FAQ retrieval and automatic question-answering, but may be useful in other contexts, such as the development of task-oriented dialogue systems, or models for natural language inference in an interrogative context. We also report on two experiments. Matching variations with their original questions was not trivial with a set of unsupervised baselines, especially for manually created variations. Besides high performances obtained with ELMo and BERT embeddings, an Information Retrieval system was surprisingly competitive when considering only the first hit. In the second experiment, text classifiers were trained with the original questions, and tested when assigning each variation to one of three possible sources, or assigning them as out-of-domain. Here, the difference between manual and automatic variations was not so significant.</abstract>
<identifier type="citekey">goncalo-oliveira-etal-2020-aia</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.669</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5442</start>
<end>5449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AIA-BDE: A Corpus of FAQs in Portuguese and their Variations
%A Gonçalo Oliveira, Hugo
%A Ferreira, João
%A Santos, José
%A Fialho, Pedro
%A Rodrigues, Ricardo
%A Coheur, Luisa
%A Alves, Ana
%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 English
%F goncalo-oliveira-etal-2020-aia
%X We present AIA-BDE, a corpus of 380 domain-oriented FAQs in Portuguese and their variations, i.e., paraphrases or entailed questions, created manually, by humans, or automatically, with Google Translate. Its aims to be used as a benchmark for FAQ retrieval and automatic question-answering, but may be useful in other contexts, such as the development of task-oriented dialogue systems, or models for natural language inference in an interrogative context. We also report on two experiments. Matching variations with their original questions was not trivial with a set of unsupervised baselines, especially for manually created variations. Besides high performances obtained with ELMo and BERT embeddings, an Information Retrieval system was surprisingly competitive when considering only the first hit. In the second experiment, text classifiers were trained with the original questions, and tested when assigning each variation to one of three possible sources, or assigning them as out-of-domain. Here, the difference between manual and automatic variations was not so significant.
%U https://aclanthology.org/2020.lrec-1.669
%P 5442-5449
Markdown (Informal)
[AIA-BDE: A Corpus of FAQs in Portuguese and their Variations](https://aclanthology.org/2020.lrec-1.669) (Gonçalo Oliveira et al., LREC 2020)
ACL
- Hugo Gonçalo Oliveira, João Ferreira, José Santos, Pedro Fialho, Ricardo Rodrigues, Luisa Coheur, and Ana Alves. 2020. AIA-BDE: A Corpus of FAQs in Portuguese and their Variations. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5442–5449, Marseille, France. European Language Resources Association.