<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lotfi-etal-2020-deep">
    <titleInfo>
        <title>A Deep Generative Approach to Native Language Identification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ehsan</namePart>
        <namePart type="family">Lotfi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ilia</namePart>
        <namePart type="family">Markov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Walter</namePart>
        <namePart type="family">Daelemans</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-dec</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 28th International Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Native language identification (NLI) – identifying the native language (L1) of a person based on his/her writing in the second language (L2) – is useful for a variety of purposes, including marketing, security, and educational applications. From a traditional machine learning perspective,NLI is usually framed as a multi-class classification task, where numerous designed features are combined in order to achieve the state-of-the-art results. We introduce a deep generative language modelling (LM) approach to NLI, which consists in fine-tuning a GPT-2 model separately on texts written by the authors with the same L1, and assigning a label to an unseen text based on the minimum LM loss with respect to one of these fine-tuned GPT-2 models. Our method outperforms traditional machine learning approaches and currently achieves the best results on the benchmark NLI datasets.</abstract>
    <identifier type="citekey">lotfi-etal-2020-deep</identifier>
    <identifier type="doi">10.18653/v1/2020.coling-main.159</identifier>
    <location>
        <url>https://aclanthology.org/2020.coling-main.159</url>
    </location>
    <part>
        <date>2020-dec</date>
        <extent unit="page">
            <start>1778</start>
            <end>1783</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Deep Generative Approach to Native Language Identification
%A Lotfi, Ehsan
%A Markov, Ilia
%A Daelemans, Walter
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 dec
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F lotfi-etal-2020-deep
%X Native language identification (NLI) – identifying the native language (L1) of a person based on his/her writing in the second language (L2) – is useful for a variety of purposes, including marketing, security, and educational applications. From a traditional machine learning perspective,NLI is usually framed as a multi-class classification task, where numerous designed features are combined in order to achieve the state-of-the-art results. We introduce a deep generative language modelling (LM) approach to NLI, which consists in fine-tuning a GPT-2 model separately on texts written by the authors with the same L1, and assigning a label to an unseen text based on the minimum LM loss with respect to one of these fine-tuned GPT-2 models. Our method outperforms traditional machine learning approaches and currently achieves the best results on the benchmark NLI datasets.
%R 10.18653/v1/2020.coling-main.159
%U https://aclanthology.org/2020.coling-main.159
%U https://doi.org/10.18653/v1/2020.coling-main.159
%P 1778-1783

Markdown (Informal)

[A Deep Generative Approach to Native Language Identification](https://aclanthology.org/2020.coling-main.159) (Lotfi et al., COLING 2020)

• A Deep Generative Approach to Native Language Identification (Lotfi et al., COLING 2020)

ACL

• Ehsan Lotfi, Ilia Markov, and Walter Daelemans. 2020. A Deep Generative Approach to Native Language Identification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1778–1783, Barcelona, Spain (Online). International Committee on Computational Linguistics.