<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2018-subword">
    <titleInfo>
        <title>Subword-level Composition Functions for Learning Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bofang</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aleksandr</namePart>
        <namePart type="family">Drozd</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyong</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop on Subword/Character LEvel Models</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Manaal</namePart>
            <namePart type="family">Faruqui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hinrich</namePart>
            <namePart type="family">Schütze</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabel</namePart>
            <namePart type="family">Trancoso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulia</namePart>
            <namePart type="family">Tsvetkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yadollah</namePart>
            <namePart type="family">Yaghoobzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries. We propose CNN- and RNN-based subword-level composition functions for learning word embeddings, and systematically compare them with popular word-level and subword-level models (Skip-Gram and FastText). Additionally, we propose a hybrid training scheme in which a pure subword-level model is trained jointly with a conventional word-level embedding model based on lookup-tables. This increases the fitness of all types of subword-level word embeddings; the word-level embeddings can be discarded after training, leaving only compact subword-level representation with much smaller data volume. We evaluate these embeddings on a set of intrinsic and extrinsic tasks, showing that subword-level models have advantage on tasks related to morphology and datasets with high OOV rate, and can be combined with other types of embeddings.</abstract>
    <identifier type="citekey">li-etal-2018-subword</identifier>
    <identifier type="doi">10.18653/v1/W18-1205</identifier>
    <location>
        <url>https://aclanthology.org/W18-1205</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>38</start>
            <end>48</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Subword-level Composition Functions for Learning Word Embeddings
%A Li, Bofang
%A Drozd, Aleksandr
%A Liu, Tao
%A Du, Xiaoyong
%Y Faruqui, Manaal
%Y Schütze, Hinrich
%Y Trancoso, Isabel
%Y Tsvetkov, Yulia
%Y Yaghoobzadeh, Yadollah
%S Proceedings of the Second Workshop on Subword/Character LEvel Models
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans
%F li-etal-2018-subword
%X Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries. We propose CNN- and RNN-based subword-level composition functions for learning word embeddings, and systematically compare them with popular word-level and subword-level models (Skip-Gram and FastText). Additionally, we propose a hybrid training scheme in which a pure subword-level model is trained jointly with a conventional word-level embedding model based on lookup-tables. This increases the fitness of all types of subword-level word embeddings; the word-level embeddings can be discarded after training, leaving only compact subword-level representation with much smaller data volume. We evaluate these embeddings on a set of intrinsic and extrinsic tasks, showing that subword-level models have advantage on tasks related to morphology and datasets with high OOV rate, and can be combined with other types of embeddings.
%R 10.18653/v1/W18-1205
%U https://aclanthology.org/W18-1205
%U https://doi.org/10.18653/v1/W18-1205
%P 38-48

Markdown (Informal)

[Subword-level Composition Functions for Learning Word Embeddings](https://aclanthology.org/W18-1205) (Li et al., SCLeM 2018)

• Subword-level Composition Functions for Learning Word Embeddings (Li et al., SCLeM 2018)

ACL

• Bofang Li, Aleksandr Drozd, Tao Liu, and Xiaoyong Du. 2018. Subword-level Composition Functions for Learning Word Embeddings. In Proceedings of the Second Workshop on Subword/Character LEvel Models, pages 38–48, New Orleans. Association for Computational Linguistics.