@inproceedings{lopez-de-lacalle-etal-2020-building,
title = "Building a Task-oriented Dialog System for Languages with no Training Data: the Case for {B}asque",
author = "L{\'o}pez de Lacalle, Maddalen and
Saralegi, Xabier and
San Vicente, I{\~n}aki",
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-1.340",
pages = "2796--2802",
abstract = "This paper presents an approach for developing a task-oriented dialog system for less-resourced languages in scenarios where training data is not available. Both intent classification and slot filling are tackled. We project the existing annotations in rich-resource languages by means of Neural Machine Translation (NMT) and posterior word alignments. We then compare training on the projected monolingual data with direct model transfer alternatives. Intent Classifiers and slot filling sequence taggers are implemented using a BiLSTM architecture or by fine-tuning BERT transformer models. Models learnt exclusively from Basque projected data provide better accuracies for slot filling. Combining Basque projected train data with rich-resource languages data outperforms consistently models trained solely on projected data for intent classification. At any rate, we achieve competitive performance in both tasks, with accuracies of 81{\%} for intent classification and 77{\%} for slot filling.",
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="lopez-de-lacalle-etal-2020-building">
<titleInfo>
<title>Building a Task-oriented Dialog System for Languages with no Training Data: the Case for Basque</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maddalen</namePart>
<namePart type="family">López de Lacalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Saralegi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="family">San Vicente</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>This paper presents an approach for developing a task-oriented dialog system for less-resourced languages in scenarios where training data is not available. Both intent classification and slot filling are tackled. We project the existing annotations in rich-resource languages by means of Neural Machine Translation (NMT) and posterior word alignments. We then compare training on the projected monolingual data with direct model transfer alternatives. Intent Classifiers and slot filling sequence taggers are implemented using a BiLSTM architecture or by fine-tuning BERT transformer models. Models learnt exclusively from Basque projected data provide better accuracies for slot filling. Combining Basque projected train data with rich-resource languages data outperforms consistently models trained solely on projected data for intent classification. At any rate, we achieve competitive performance in both tasks, with accuracies of 81% for intent classification and 77% for slot filling.</abstract>
<identifier type="citekey">lopez-de-lacalle-etal-2020-building</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.340</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2796</start>
<end>2802</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Task-oriented Dialog System for Languages with no Training Data: the Case for Basque
%A López de Lacalle, Maddalen
%A Saralegi, Xabier
%A San Vicente, Iñaki
%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 lopez-de-lacalle-etal-2020-building
%X This paper presents an approach for developing a task-oriented dialog system for less-resourced languages in scenarios where training data is not available. Both intent classification and slot filling are tackled. We project the existing annotations in rich-resource languages by means of Neural Machine Translation (NMT) and posterior word alignments. We then compare training on the projected monolingual data with direct model transfer alternatives. Intent Classifiers and slot filling sequence taggers are implemented using a BiLSTM architecture or by fine-tuning BERT transformer models. Models learnt exclusively from Basque projected data provide better accuracies for slot filling. Combining Basque projected train data with rich-resource languages data outperforms consistently models trained solely on projected data for intent classification. At any rate, we achieve competitive performance in both tasks, with accuracies of 81% for intent classification and 77% for slot filling.
%U https://aclanthology.org/2020.lrec-1.340
%P 2796-2802
Markdown (Informal)
[Building a Task-oriented Dialog System for Languages with no Training Data: the Case for Basque](https://aclanthology.org/2020.lrec-1.340) (López de Lacalle et al., LREC 2020)
ACL