@inproceedings{goswami-etal-2024-native,
title = "Native Language Identification in Texts: A Survey",
author = "Goswami, Dhiman and
Thilagan, Sharanya and
North, Kai and
Malmasi, Shervin and
Zampieri, Marcos",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.173",
pages = "3149--3160",
abstract = "We present the first comprehensive survey of Native Language Identification (NLI) applied to texts. NLI is the task of automatically identifying an author{'}s native language (L1) based on their second language (L2) production. NLI is an important task with practical applications in second language teaching and NLP. The task has been widely studied for both text and speech, particularly for L2 English due to the availability of suitable corpora. Speech-based NLI relies heavily on accent modeled by pronunciation patterns and prosodic cues while text-based NLI relies primarily on modeling spelling errors and grammatical patterns that reveal properties of an individuals{'} L1 influencing L2 production. We survey over one hundred papers on the topic including the papers associated with the NLI and INLI shared tasks. We describe several text representations and computational techniques used in text-based NLI. Finally, we present a comprehensive account of publicly available datasets used for the task thus far.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goswami-etal-2024-native">
<titleInfo>
<title>Native Language Identification in Texts: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhiman</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharanya</namePart>
<namePart type="family">Thilagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the first comprehensive survey of Native Language Identification (NLI) applied to texts. NLI is the task of automatically identifying an author’s native language (L1) based on their second language (L2) production. NLI is an important task with practical applications in second language teaching and NLP. The task has been widely studied for both text and speech, particularly for L2 English due to the availability of suitable corpora. Speech-based NLI relies heavily on accent modeled by pronunciation patterns and prosodic cues while text-based NLI relies primarily on modeling spelling errors and grammatical patterns that reveal properties of an individuals’ L1 influencing L2 production. We survey over one hundred papers on the topic including the papers associated with the NLI and INLI shared tasks. We describe several text representations and computational techniques used in text-based NLI. Finally, we present a comprehensive account of publicly available datasets used for the task thus far.</abstract>
<identifier type="citekey">goswami-etal-2024-native</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.173</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>3149</start>
<end>3160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Native Language Identification in Texts: A Survey
%A Goswami, Dhiman
%A Thilagan, Sharanya
%A North, Kai
%A Malmasi, Shervin
%A Zampieri, Marcos
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F goswami-etal-2024-native
%X We present the first comprehensive survey of Native Language Identification (NLI) applied to texts. NLI is the task of automatically identifying an author’s native language (L1) based on their second language (L2) production. NLI is an important task with practical applications in second language teaching and NLP. The task has been widely studied for both text and speech, particularly for L2 English due to the availability of suitable corpora. Speech-based NLI relies heavily on accent modeled by pronunciation patterns and prosodic cues while text-based NLI relies primarily on modeling spelling errors and grammatical patterns that reveal properties of an individuals’ L1 influencing L2 production. We survey over one hundred papers on the topic including the papers associated with the NLI and INLI shared tasks. We describe several text representations and computational techniques used in text-based NLI. Finally, we present a comprehensive account of publicly available datasets used for the task thus far.
%U https://aclanthology.org/2024.naacl-long.173
%P 3149-3160
Markdown (Informal)
[Native Language Identification in Texts: A Survey](https://aclanthology.org/2024.naacl-long.173) (Goswami et al., NAACL 2024)
ACL
- Dhiman Goswami, Sharanya Thilagan, Kai North, Shervin Malmasi, and Marcos Zampieri. 2024. Native Language Identification in Texts: A Survey. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3149–3160, Mexico City, Mexico. Association for Computational Linguistics.