<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jhan-etal-2022-c5l7">
    <titleInfo>
        <title>C5L7: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiun-hao</namePart>
        <namePart type="family">Jhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qingxiaoyang</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nehal</namePart>
        <namePart type="family">Bengre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tapas</namePart>
        <namePart type="family">Kanungo</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>Voice assistants are becoming central to our lives. The convenience of using voice assistants to do simple tasks has created an industry for voice-enabled devices like TVs, thermostats, air conditioners, etc. It has also improved the quality of life of elders by making the world more accessible. Voice assistants engage in task-oriented dialogues using machine-learned language understanding models. However, training deep-learned models take a lot of training data, which is time-consuming and expensive. Furthermore, it is even more problematic if we want the voice assistant to understand hundreds of languages. In this paper, we present a zero-shot deep learning algorithm that uses only the English part of the Massive dataset and achieves a high level of accuracy across 51 languages. The algorithm uses a delexicalized translation model to generate multilingual data for data augmentation. The training data is further weighted to improve the accuracy of the worst-performing languages. We report on our experiments with code-switching, word order, multilingual ensemble methods, and other techniques and their impact on overall accuracy.</abstract>
    <identifier type="citekey">jhan-etal-2022-c5l7</identifier>
    <identifier type="doi">10.18653/v1/2022.mmnlu-1.7</identifier>
    <location>
        <url>https://aclanthology.org/2022.mmnlu-1.7/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>62</start>
            <end>68</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T C5L7: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages
%A Jhan, Jiun-hao
%A Zhu, Qingxiaoyang
%A Bengre, Nehal
%A Kanungo, Tapas
%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 jhan-etal-2022-c5l7
%X Voice assistants are becoming central to our lives. The convenience of using voice assistants to do simple tasks has created an industry for voice-enabled devices like TVs, thermostats, air conditioners, etc. It has also improved the quality of life of elders by making the world more accessible. Voice assistants engage in task-oriented dialogues using machine-learned language understanding models. However, training deep-learned models take a lot of training data, which is time-consuming and expensive. Furthermore, it is even more problematic if we want the voice assistant to understand hundreds of languages. In this paper, we present a zero-shot deep learning algorithm that uses only the English part of the Massive dataset and achieves a high level of accuracy across 51 languages. The algorithm uses a delexicalized translation model to generate multilingual data for data augmentation. The training data is further weighted to improve the accuracy of the worst-performing languages. We report on our experiments with code-switching, word order, multilingual ensemble methods, and other techniques and their impact on overall accuracy.
%R 10.18653/v1/2022.mmnlu-1.7
%U https://aclanthology.org/2022.mmnlu-1.7/
%U https://doi.org/10.18653/v1/2022.mmnlu-1.7
%P 62-68

Markdown (Informal)

[C5L7: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages](https://aclanthology.org/2022.mmnlu-1.7/) (Jhan et al., MMNLU 2022)

• C5L7: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages (Jhan et al., MMNLU 2022)

ACL

• Jiun-hao Jhan, Qingxiaoyang Zhu, Nehal Bengre, and Tapas Kanungo. 2022. C5L7: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages. In Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22), pages 62–68, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.