<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malaviya-etal-2017-learning">
    <titleInfo>
        <title>Learning Language Representations for Typology Prediction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chaitanya</namePart>
        <namePart type="family">Malaviya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Patrick</namePart>
        <namePart type="family">Littell</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>One central mystery of neural NLP is what neural models “know” about their subject matter. When a neural machine translation system learns to translate from one language to another, does it learn the syntax or semantics of the languages? Can this knowledge be extracted from the system to fill holes in human scientific knowledge? Existing typological databases contain relatively full feature specifications for only a few hundred languages. Exploiting the existence of parallel texts in more than a thousand languages, we build a massive many-to-one NMT system from 1017 languages into English, and use this to predict information missing from typological databases. Experiments show that the proposed method is able to infer not only syntactic, but also phonological and phonetic inventory features, and improves over a baseline that has access to information about the languages geographic and phylogenetic neighbors.</abstract>
    <identifier type="citekey">malaviya-etal-2017-learning</identifier>
    <identifier type="doi">10.18653/v1/D17-1268</identifier>
    <location>
        <url>https://aclanthology.org/D17-1268</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>2529</start>
            <end>2535</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Language Representations for Typology Prediction
%A Malaviya, Chaitanya
%A Neubig, Graham
%A Littell, Patrick
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F malaviya-etal-2017-learning
%X One central mystery of neural NLP is what neural models “know” about their subject matter. When a neural machine translation system learns to translate from one language to another, does it learn the syntax or semantics of the languages? Can this knowledge be extracted from the system to fill holes in human scientific knowledge? Existing typological databases contain relatively full feature specifications for only a few hundred languages. Exploiting the existence of parallel texts in more than a thousand languages, we build a massive many-to-one NMT system from 1017 languages into English, and use this to predict information missing from typological databases. Experiments show that the proposed method is able to infer not only syntactic, but also phonological and phonetic inventory features, and improves over a baseline that has access to information about the languages geographic and phylogenetic neighbors.
%R 10.18653/v1/D17-1268
%U https://aclanthology.org/D17-1268
%U https://doi.org/10.18653/v1/D17-1268
%P 2529-2535

Markdown (Informal)

[Learning Language Representations for Typology Prediction](https://aclanthology.org/D17-1268) (Malaviya et al., EMNLP 2017)

• Learning Language Representations for Typology Prediction (Malaviya et al., EMNLP 2017)

ACL

• Chaitanya Malaviya, Graham Neubig, and Patrick Littell. 2017. Learning Language Representations for Typology Prediction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2529–2535, Copenhagen, Denmark. Association for Computational Linguistics.