<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-bruyn-etal-2022-machine">
    <titleInfo>
        <title>Machine Translation for Multilingual Intent Detection and Slots Filling</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>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jack</namePart>
            <namePart type="family">FitzGerald</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kay</namePart>
            <namePart type="family">Rottmann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hirschberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rumshisky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Charith</namePart>
            <namePart type="family">Peris</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Hench</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We expect to interact with home assistants irrespective of our language. However, scaling the Natural Language Understanding pipeline to multiple languages while keeping the same level of accuracy remains a challenge. In this work, we leverage the inherent multilingual aspect of translation models for the task of multilingual intent classification and slot filling. Our experiments reveal that they work equally well with general-purpose multilingual text-to-text models. Furthermore, their accuracy can be further improved by artificially increasing the size of the training set. Unfortunately, increasing the training set also increases the overlap with the test set, leading to overestimating their true capabilities. As a result, we propose two new evaluation methods capable of accounting for an overlap between the training and test set.</abstract>
    <identifier type="citekey">de-bruyn-etal-2022-machine</identifier>
    <identifier type="doi">10.18653/v1/2022.mmnlu-1.8</identifier>
    <location>
        <url>https://aclanthology.org/2022.mmnlu-1.8/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>69</start>
            <end>82</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Machine Translation for Multilingual Intent Detection and Slots Filling
%A De bruyn, Maxime
%A Lotfi, Ehsan
%A Buhmann, Jeska
%A Daelemans, Walter
%Y FitzGerald, Jack
%Y Rottmann, Kay
%Y Hirschberg, Julia
%Y Bansal, Mohit
%Y Rumshisky, Anna
%Y Peris, Charith
%Y Hench, Christopher
%S Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F de-bruyn-etal-2022-machine
%X We expect to interact with home assistants irrespective of our language. However, scaling the Natural Language Understanding pipeline to multiple languages while keeping the same level of accuracy remains a challenge. In this work, we leverage the inherent multilingual aspect of translation models for the task of multilingual intent classification and slot filling. Our experiments reveal that they work equally well with general-purpose multilingual text-to-text models. Furthermore, their accuracy can be further improved by artificially increasing the size of the training set. Unfortunately, increasing the training set also increases the overlap with the test set, leading to overestimating their true capabilities. As a result, we propose two new evaluation methods capable of accounting for an overlap between the training and test set.
%R 10.18653/v1/2022.mmnlu-1.8
%U https://aclanthology.org/2022.mmnlu-1.8/
%U https://doi.org/10.18653/v1/2022.mmnlu-1.8
%P 69-82

Markdown (Informal)

[Machine Translation for Multilingual Intent Detection and Slots Filling](https://aclanthology.org/2022.mmnlu-1.8/) (De bruyn et al., MMNLU 2022)

• Machine Translation for Multilingual Intent Detection and Slots Filling (De bruyn et al., MMNLU 2022)

ACL

• Maxime De bruyn, Ehsan Lotfi, Jeska Buhmann, and Walter Daelemans. 2022. Machine Translation for Multilingual Intent Detection and Slots Filling. In Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22), pages 69–82, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.