@inproceedings{dobrossy-etal-2019-investigating,
title = "Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order {H}ungarian",
author = {D{\"o}br{\"o}ssy, B{\'a}lint and
Makrai, M{\'a}rton and
Tarj{\'a}n, Bal{\'a}zs and
Szasz{\'a}k, Gy{\"o}rgy},
editor = "Augenstein, Isabelle and
Gella, Spandana and
Ruder, Sebastian and
Kann, Katharina and
Can, Burcu and
Welbl, Johannes and
Conneau, Alexis and
Ren, Xiang and
Rei, Marek",
booktitle = "Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4321",
doi = "10.18653/v1/W19-4321",
pages = "187--193",
abstract = "For morphologically rich languages, word embeddings provide less consistent semantic representations due to higher variance in word forms. Moreover, these languages often allow for less constrained word order, which further increases variance. For the highly agglutinative Hungarian, semantic accuracy of word embeddings measured on word analogy tasks drops by 50-75{\%} compared to English. We observed that embeddings learn morphosyntax quite well instead. Therefore, we explore and evaluate several sub-word unit based embedding strategies {--} character n-grams, lemmatization provided by an NLP-pipeline, and segments obtained in unsupervised learning (morfessor) {--} to boost semantic consistency in Hungarian word vectors. The effect of changing embedding dimension and context window size have also been considered. Morphological analysis based lemmatization was found to be the best strategy to improve embeddings{'} semantic accuracy, whereas adding character n-grams was found consistently counterproductive in this regard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobrossy-etal-2019-investigating">
<titleInfo>
<title>Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bálint</namePart>
<namePart type="family">Döbrössy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Márton</namePart>
<namePart type="family">Makrai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balázs</namePart>
<namePart type="family">Tarján</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Szaszák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For morphologically rich languages, word embeddings provide less consistent semantic representations due to higher variance in word forms. Moreover, these languages often allow for less constrained word order, which further increases variance. For the highly agglutinative Hungarian, semantic accuracy of word embeddings measured on word analogy tasks drops by 50-75% compared to English. We observed that embeddings learn morphosyntax quite well instead. Therefore, we explore and evaluate several sub-word unit based embedding strategies – character n-grams, lemmatization provided by an NLP-pipeline, and segments obtained in unsupervised learning (morfessor) – to boost semantic consistency in Hungarian word vectors. The effect of changing embedding dimension and context window size have also been considered. Morphological analysis based lemmatization was found to be the best strategy to improve embeddings’ semantic accuracy, whereas adding character n-grams was found consistently counterproductive in this regard.</abstract>
<identifier type="citekey">dobrossy-etal-2019-investigating</identifier>
<identifier type="doi">10.18653/v1/W19-4321</identifier>
<location>
<url>https://aclanthology.org/W19-4321</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>187</start>
<end>193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian
%A Döbrössy, Bálint
%A Makrai, Márton
%A Tarján, Balázs
%A Szaszák, György
%Y Augenstein, Isabelle
%Y Gella, Spandana
%Y Ruder, Sebastian
%Y Kann, Katharina
%Y Can, Burcu
%Y Welbl, Johannes
%Y Conneau, Alexis
%Y Ren, Xiang
%Y Rei, Marek
%S Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F dobrossy-etal-2019-investigating
%X For morphologically rich languages, word embeddings provide less consistent semantic representations due to higher variance in word forms. Moreover, these languages often allow for less constrained word order, which further increases variance. For the highly agglutinative Hungarian, semantic accuracy of word embeddings measured on word analogy tasks drops by 50-75% compared to English. We observed that embeddings learn morphosyntax quite well instead. Therefore, we explore and evaluate several sub-word unit based embedding strategies – character n-grams, lemmatization provided by an NLP-pipeline, and segments obtained in unsupervised learning (morfessor) – to boost semantic consistency in Hungarian word vectors. The effect of changing embedding dimension and context window size have also been considered. Morphological analysis based lemmatization was found to be the best strategy to improve embeddings’ semantic accuracy, whereas adding character n-grams was found consistently counterproductive in this regard.
%R 10.18653/v1/W19-4321
%U https://aclanthology.org/W19-4321
%U https://doi.org/10.18653/v1/W19-4321
%P 187-193
Markdown (Informal)
[Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian](https://aclanthology.org/W19-4321) (Döbrössy et al., RepL4NLP 2019)
ACL