<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pylypenko-etal-2021-comparing">
    <titleInfo>
        <title>Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daria</namePart>
        <namePart type="family">Pylypenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kwabena</namePart>
        <namePart type="family">Amponsah-Kaakyire</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Koel</namePart>
        <namePart type="family">Dutta Chowdhury</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">van Genabith</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cristina</namePart>
        <namePart type="family">España-Bonet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been less explored for this task. In this work, we (i) compare the traditional feature-engineering-based approach to the feature-learning-based one and (ii) analyse the neural architectures in order to investigate how well the hand-crafted features explain the variance in the neural models’ predictions. We use pre-trained neural word embeddings, as well as several end-to-end neural architectures in both monolingual and multilingual settings and compare them to feature-engineering-based SVM classifiers. We show that (i) neural architectures outperform other approaches by more than 20 accuracy points, with the BERT-based model performing the best in both the monolingual and multilingual settings; (ii) while many individual hand-crafted translationese features correlate with neural model predictions, feature importance analysis shows that the most important features for neural and classical architectures differ; and (iii) our multilingual experiments provide empirical evidence for translationese universals across languages.</abstract>
    <identifier type="citekey">pylypenko-etal-2021-comparing</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.676</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.676</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>8596</start>
            <end>8611</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification
%A Pylypenko, Daria
%A Amponsah-Kaakyire, Kwabena
%A Dutta Chowdhury, Koel
%A van Genabith, Josef
%A España-Bonet, Cristina
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F pylypenko-etal-2021-comparing
%X Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been less explored for this task. In this work, we (i) compare the traditional feature-engineering-based approach to the feature-learning-based one and (ii) analyse the neural architectures in order to investigate how well the hand-crafted features explain the variance in the neural models’ predictions. We use pre-trained neural word embeddings, as well as several end-to-end neural architectures in both monolingual and multilingual settings and compare them to feature-engineering-based SVM classifiers. We show that (i) neural architectures outperform other approaches by more than 20 accuracy points, with the BERT-based model performing the best in both the monolingual and multilingual settings; (ii) while many individual hand-crafted translationese features correlate with neural model predictions, feature importance analysis shows that the most important features for neural and classical architectures differ; and (iii) our multilingual experiments provide empirical evidence for translationese universals across languages.
%R 10.18653/v1/2021.emnlp-main.676
%U https://aclanthology.org/2021.emnlp-main.676
%U https://doi.org/10.18653/v1/2021.emnlp-main.676
%P 8596-8611

Markdown (Informal)

[Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification](https://aclanthology.org/2021.emnlp-main.676) (Pylypenko et al., EMNLP 2021)

• Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification (Pylypenko et al., EMNLP 2021)

ACL

• Daria Pylypenko, Kwabena Amponsah-Kaakyire, Koel Dutta Chowdhury, Josef van Genabith, and Cristina España-Bonet. 2021. Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8596–8611, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.