<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruzsics-samardzic-2017-neural">
    <titleInfo>
        <title>Neural Sequence-to-sequence Learning of Internal Word Structure</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tatyana</namePart>
        <namePart type="family">Ruzsics</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tanja</namePart>
        <namePart type="family">Samardžić</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Roger</namePart>
            <namePart type="family">Levy</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>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Learning internal word structure has recently been recognized as an important step in various multilingual processing tasks and in theoretical language comparison. In this paper, we present a neural encoder-decoder model for learning canonical morphological segmentation. Our model combines character-level sequence-to-sequence transformation with a language model over canonical segments. We obtain up to 4% improvement over a strong character-level encoder-decoder baseline for three languages. Our model outperforms the previous state-of-the-art for two languages, while eliminating the need for external resources such as large dictionaries. Finally, by comparing the performance of encoder-decoder and classical statistical machine translation systems trained with and without corpus counts, we show that including corpus counts is beneficial to both approaches.</abstract>
    <identifier type="citekey">ruzsics-samardzic-2017-neural</identifier>
    <identifier type="doi">10.18653/v1/K17-1020</identifier>
    <location>
        <url>https://aclanthology.org/K17-1020</url>
    </location>
    <part>
        <date>2017-08</date>
        <extent unit="page">
            <start>184</start>
            <end>194</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Neural Sequence-to-sequence Learning of Internal Word Structure
%A Ruzsics, Tatyana
%A Samardžić, Tanja
%Y Levy, Roger
%Y Specia, Lucia
%S Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F ruzsics-samardzic-2017-neural
%X Learning internal word structure has recently been recognized as an important step in various multilingual processing tasks and in theoretical language comparison. In this paper, we present a neural encoder-decoder model for learning canonical morphological segmentation. Our model combines character-level sequence-to-sequence transformation with a language model over canonical segments. We obtain up to 4% improvement over a strong character-level encoder-decoder baseline for three languages. Our model outperforms the previous state-of-the-art for two languages, while eliminating the need for external resources such as large dictionaries. Finally, by comparing the performance of encoder-decoder and classical statistical machine translation systems trained with and without corpus counts, we show that including corpus counts is beneficial to both approaches.
%R 10.18653/v1/K17-1020
%U https://aclanthology.org/K17-1020
%U https://doi.org/10.18653/v1/K17-1020
%P 184-194

Markdown (Informal)

[Neural Sequence-to-sequence Learning of Internal Word Structure](https://aclanthology.org/K17-1020) (Ruzsics & Samardžić, CoNLL 2017)

• Neural Sequence-to-sequence Learning of Internal Word Structure (Ruzsics & Samardžić, CoNLL 2017)

ACL

• Tatyana Ruzsics and Tanja Samardžić. 2017. Neural Sequence-to-sequence Learning of Internal Word Structure. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 184–194, Vancouver, Canada. Association for Computational Linguistics.