@inproceedings{wang-etal-2022-zero,
title = "Zero-Shot Cross-Lingual Sequence Tagging as {S}eq2{S}eq Generation for Joint Intent Classification and Slot Filling",
author = "Wang, Fei and
Huang, Kuan-hao and
Kumar, Anoop and
Galstyan, Aram and
Ver steeg, Greg and
Chang, Kai-wei",
editor = "FitzGerald, Jack and
Rottmann, Kay and
Hirschberg, Julia and
Bansal, Mohit and
Rumshisky, Anna and
Peris, Charith and
Hench, Christopher",
booktitle = "Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mmnlu-1.6/",
doi = "10.18653/v1/2022.mmnlu-1.6",
pages = "53--61",
abstract = "The joint intent classification and slot filling task seeks to detect the intent of an utterance and extract its semantic concepts. In the zero-shot cross-lingual setting, a model is trained on a source language and then transferred to other target languages through multi-lingual representations without additional training data. While prior studies show that pre-trained multilingual sequence-to-sequence (Seq2Seq) models can facilitate zero-shot transfer, there is little understanding on how to design the output template for the joint prediction tasks. In this paper, we examine three aspects of the output template {--} (1) label mapping, (2) task dependency, and (3) word order. Experiments on the MASSIVE dataset consisting of 51 languages show that our output template significantly improves the performance of pre-trained cross-lingual language models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-zero">
<titleInfo>
<title>Zero-Shot Cross-Lingual Sequence Tagging as Seq2Seq Generation for Joint Intent Classification and Slot Filling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-hao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galstyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Ver steeg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-wei</namePart>
<namePart type="family">Chang</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>The joint intent classification and slot filling task seeks to detect the intent of an utterance and extract its semantic concepts. In the zero-shot cross-lingual setting, a model is trained on a source language and then transferred to other target languages through multi-lingual representations without additional training data. While prior studies show that pre-trained multilingual sequence-to-sequence (Seq2Seq) models can facilitate zero-shot transfer, there is little understanding on how to design the output template for the joint prediction tasks. In this paper, we examine three aspects of the output template – (1) label mapping, (2) task dependency, and (3) word order. Experiments on the MASSIVE dataset consisting of 51 languages show that our output template significantly improves the performance of pre-trained cross-lingual language models.</abstract>
<identifier type="citekey">wang-etal-2022-zero</identifier>
<identifier type="doi">10.18653/v1/2022.mmnlu-1.6</identifier>
<location>
<url>https://aclanthology.org/2022.mmnlu-1.6/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>53</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Cross-Lingual Sequence Tagging as Seq2Seq Generation for Joint Intent Classification and Slot Filling
%A Wang, Fei
%A Huang, Kuan-hao
%A Kumar, Anoop
%A Galstyan, Aram
%A Ver steeg, Greg
%A Chang, Kai-wei
%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 wang-etal-2022-zero
%X The joint intent classification and slot filling task seeks to detect the intent of an utterance and extract its semantic concepts. In the zero-shot cross-lingual setting, a model is trained on a source language and then transferred to other target languages through multi-lingual representations without additional training data. While prior studies show that pre-trained multilingual sequence-to-sequence (Seq2Seq) models can facilitate zero-shot transfer, there is little understanding on how to design the output template for the joint prediction tasks. In this paper, we examine three aspects of the output template – (1) label mapping, (2) task dependency, and (3) word order. Experiments on the MASSIVE dataset consisting of 51 languages show that our output template significantly improves the performance of pre-trained cross-lingual language models.
%R 10.18653/v1/2022.mmnlu-1.6
%U https://aclanthology.org/2022.mmnlu-1.6/
%U https://doi.org/10.18653/v1/2022.mmnlu-1.6
%P 53-61
Markdown (Informal)
[Zero-Shot Cross-Lingual Sequence Tagging as Seq2Seq Generation for Joint Intent Classification and Slot Filling](https://aclanthology.org/2022.mmnlu-1.6/) (Wang et al., MMNLU 2022)
ACL