@inproceedings{holt-etal-2024-perceptions,
title = "Perceptions of Language Technology Failures from {S}outh {A}sian {E}nglish Speakers",
author = "Holt, Faye and
Held, William and
Yang, Diyi",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.241",
pages = "4067--4081",
abstract = "English NLP systems have empirically worse performance for dialects other than Standard American English (SAmE). However, how these discrepancies impact use of language technology by speakers of non-SAmE global Englishes is not well understood. We focus on reducing this gap for South Asian Englishes (SAsE), a macro-group of regional varieties with cumulatively more speakers than SAmE, by surveying SAsE speakers about their interactions with language technology and compare their responses to a control survey of SAmE speakers. SAsE speakers are more likely to recall failures with language technology and more likely to reference specific issues with written language technology than their SAmE counterparts. Furthermore, SAsE speakers indicate that they modify both their lexicon and syntax to make technology work better, but that lexical issues are perceived as the most salient challenge. We then assess whether these issues are pervasive in more recently developed Large Language Models (LLMs), introducing two benchmarks for broader SAsE Lexical and Indian English Syntactic understanding and evaluating 11 families of LLMs on them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="holt-etal-2024-perceptions">
<titleInfo>
<title>Perceptions of Language Technology Failures from South Asian English Speakers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Faye</namePart>
<namePart type="family">Holt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Held</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>English NLP systems have empirically worse performance for dialects other than Standard American English (SAmE). However, how these discrepancies impact use of language technology by speakers of non-SAmE global Englishes is not well understood. We focus on reducing this gap for South Asian Englishes (SAsE), a macro-group of regional varieties with cumulatively more speakers than SAmE, by surveying SAsE speakers about their interactions with language technology and compare their responses to a control survey of SAmE speakers. SAsE speakers are more likely to recall failures with language technology and more likely to reference specific issues with written language technology than their SAmE counterparts. Furthermore, SAsE speakers indicate that they modify both their lexicon and syntax to make technology work better, but that lexical issues are perceived as the most salient challenge. We then assess whether these issues are pervasive in more recently developed Large Language Models (LLMs), introducing two benchmarks for broader SAsE Lexical and Indian English Syntactic understanding and evaluating 11 families of LLMs on them.</abstract>
<identifier type="citekey">holt-etal-2024-perceptions</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.241</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4067</start>
<end>4081</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perceptions of Language Technology Failures from South Asian English Speakers
%A Holt, Faye
%A Held, William
%A Yang, Diyi
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F holt-etal-2024-perceptions
%X English NLP systems have empirically worse performance for dialects other than Standard American English (SAmE). However, how these discrepancies impact use of language technology by speakers of non-SAmE global Englishes is not well understood. We focus on reducing this gap for South Asian Englishes (SAsE), a macro-group of regional varieties with cumulatively more speakers than SAmE, by surveying SAsE speakers about their interactions with language technology and compare their responses to a control survey of SAmE speakers. SAsE speakers are more likely to recall failures with language technology and more likely to reference specific issues with written language technology than their SAmE counterparts. Furthermore, SAsE speakers indicate that they modify both their lexicon and syntax to make technology work better, but that lexical issues are perceived as the most salient challenge. We then assess whether these issues are pervasive in more recently developed Large Language Models (LLMs), introducing two benchmarks for broader SAsE Lexical and Indian English Syntactic understanding and evaluating 11 families of LLMs on them.
%U https://aclanthology.org/2024.findings-acl.241
%P 4067-4081
Markdown (Informal)
[Perceptions of Language Technology Failures from South Asian English Speakers](https://aclanthology.org/2024.findings-acl.241) (Holt et al., Findings 2024)
ACL