@inproceedings{wang-etal-2022-benchmarking,
title = "Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms",
author = "Wang, Gengyu and
Qian, Cheng and
Pan, Lin and
Qi, Haode and
Kunc, Ladislav and
Potdar, Saloni",
editor = "Asai, Akari and
Choi, Eunsol and
Clark, Jonathan H. and
Hu, Junjie and
Lee, Chia-Hsuan and
Kasai, Jungo and
Longpre, Shayne and
Yamada, Ikuya and
Zhang, Rui",
booktitle = "Proceedings of the Workshop on Multilingual Information Access (MIA)",
month = jul,
year = "2022",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mia-1.7",
doi = "10.18653/v1/2022.mia-1.7",
pages = "69--76",
abstract = "Current virtual assistant (VA) platforms are beholden to the limited number of languages they support. Every component, such as the tokenizer and intent classifier, is engineered for specific languages in these intricate platforms. Thus, supporting a new language in such platforms is a resource-intensive operation requiring expensive re-training and re-designing. In this paper, we propose a benchmark for evaluating language-agnostic intent classification, the most critical component of VA platforms. To ensure the benchmarking is challenging and comprehensive, we include 29 public and internal datasets across 10 low-resource languages and evaluate various training and testing settings with consideration of both accuracy and training time. The benchmarking result shows that Watson Assistant, among 7 commercial VA platforms and pre-trained multilingual language models (LMs), demonstrates close-to-best accuracy with the best accuracy-training time trade-off.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-benchmarking">
<titleInfo>
<title>Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haode</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ladislav</namePart>
<namePart type="family">Kunc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Multilingual Information Access (MIA)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hsuan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungo</namePart>
<namePart type="family">Kasai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shayne</namePart>
<namePart type="family">Longpre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ikuya</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current virtual assistant (VA) platforms are beholden to the limited number of languages they support. Every component, such as the tokenizer and intent classifier, is engineered for specific languages in these intricate platforms. Thus, supporting a new language in such platforms is a resource-intensive operation requiring expensive re-training and re-designing. In this paper, we propose a benchmark for evaluating language-agnostic intent classification, the most critical component of VA platforms. To ensure the benchmarking is challenging and comprehensive, we include 29 public and internal datasets across 10 low-resource languages and evaluate various training and testing settings with consideration of both accuracy and training time. The benchmarking result shows that Watson Assistant, among 7 commercial VA platforms and pre-trained multilingual language models (LMs), demonstrates close-to-best accuracy with the best accuracy-training time trade-off.</abstract>
<identifier type="citekey">wang-etal-2022-benchmarking</identifier>
<identifier type="doi">10.18653/v1/2022.mia-1.7</identifier>
<location>
<url>https://aclanthology.org/2022.mia-1.7</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>69</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms
%A Wang, Gengyu
%A Qian, Cheng
%A Pan, Lin
%A Qi, Haode
%A Kunc, Ladislav
%A Potdar, Saloni
%Y Asai, Akari
%Y Choi, Eunsol
%Y Clark, Jonathan H.
%Y Hu, Junjie
%Y Lee, Chia-Hsuan
%Y Kasai, Jungo
%Y Longpre, Shayne
%Y Yamada, Ikuya
%Y Zhang, Rui
%S Proceedings of the Workshop on Multilingual Information Access (MIA)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F wang-etal-2022-benchmarking
%X Current virtual assistant (VA) platforms are beholden to the limited number of languages they support. Every component, such as the tokenizer and intent classifier, is engineered for specific languages in these intricate platforms. Thus, supporting a new language in such platforms is a resource-intensive operation requiring expensive re-training and re-designing. In this paper, we propose a benchmark for evaluating language-agnostic intent classification, the most critical component of VA platforms. To ensure the benchmarking is challenging and comprehensive, we include 29 public and internal datasets across 10 low-resource languages and evaluate various training and testing settings with consideration of both accuracy and training time. The benchmarking result shows that Watson Assistant, among 7 commercial VA platforms and pre-trained multilingual language models (LMs), demonstrates close-to-best accuracy with the best accuracy-training time trade-off.
%R 10.18653/v1/2022.mia-1.7
%U https://aclanthology.org/2022.mia-1.7
%U https://doi.org/10.18653/v1/2022.mia-1.7
%P 69-76
Markdown (Informal)
[Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms](https://aclanthology.org/2022.mia-1.7) (Wang et al., MIA 2022)
ACL