<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ek-bernardy-2020-composing">
    <titleInfo>
        <title>Composing Byte-Pair Encodings for Morphological Sequence Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Ek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Philippe</namePart>
        <namePart type="family">Bernardy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Universal Dependencies (UDW 2020)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Miryam</namePart>
            <namePart type="family">de Lhoneux</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joakim</namePart>
            <namePart type="family">Nivre</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Schuster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Byte-pair encodings is a method for splitting a word into sub-word tokens, a language model then assigns contextual representations separately to each of these tokens. In this paper, we evaluate four different methods of composing such sub-word representations into word representations. We evaluate the methods on morphological sequence classification, the task of predicting grammatical features of a word. Our experiments reveal that using an RNN to compute word representations is consistently more effective than the other methods tested across a sample of eight languages with different typology and varying numbers of byte-pair tokens per word.</abstract>
    <identifier type="citekey">ek-bernardy-2020-composing</identifier>
    <location>
        <url>https://aclanthology.org/2020.udw-1.9/</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>76</start>
            <end>86</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Composing Byte-Pair Encodings for Morphological Sequence Classification
%A Ek, Adam
%A Bernardy, Jean-Philippe
%Y de Marneffe, Marie-Catherine
%Y de Lhoneux, Miryam
%Y Nivre, Joakim
%Y Schuster, Sebastian
%S Proceedings of the Fourth Workshop on Universal Dependencies (UDW 2020)
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F ek-bernardy-2020-composing
%X Byte-pair encodings is a method for splitting a word into sub-word tokens, a language model then assigns contextual representations separately to each of these tokens. In this paper, we evaluate four different methods of composing such sub-word representations into word representations. We evaluate the methods on morphological sequence classification, the task of predicting grammatical features of a word. Our experiments reveal that using an RNN to compute word representations is consistently more effective than the other methods tested across a sample of eight languages with different typology and varying numbers of byte-pair tokens per word.
%U https://aclanthology.org/2020.udw-1.9/
%P 76-86

Markdown (Informal)

[Composing Byte-Pair Encodings for Morphological Sequence Classification](https://aclanthology.org/2020.udw-1.9/) (Ek & Bernardy, UDW 2020)

• Composing Byte-Pair Encodings for Morphological Sequence Classification (Ek & Bernardy, UDW 2020)

ACL

• Adam Ek and Jean-Philippe Bernardy. 2020. Composing Byte-Pair Encodings for Morphological Sequence Classification. In Proceedings of the Fourth Workshop on Universal Dependencies (UDW 2020), pages 76–86, Barcelona, Spain (Online). Association for Computational Linguistics.