Cross-Lingual Word Embeddings for Morphologically Rich Languages

Ahmet Üstün; Gosse Bouma; Gerardus Noord, van

doi:10.26615/978-954-452-056-4_140

Cross-Lingual Word Embeddings for Morphologically Rich Languages

Ahmet Üstün, Gosse Bouma, Gerardus Noord, van

Research output: Contribution to conference › Paper › Academic

17 Downloads (Pure)

Abstract

Cross-lingual word embedding models learn
a shared vector space for two or more lan-
guages so that words with similar meaning
are represented by similar vectors regardless
of their language. Although the existing mod-
els achieve high performance on pairs of mor-
phologically simple languages, they perform
very poorly on morphologically rich languages
such as Turkish and Finnish. In this pa-
per, we propose a morpheme-based model in
order to increase the performance of cross-
lingual word embeddings on morphologically
rich languages. Our model includes a sim-
ple extension which enables us to exploit mor-
phemes for cross-lingual mapping. We ap-
plied our model for the Turkish-Finnish lan-
guage pair on the bilingual word translation
task. Results show that our model outper-
forms the baseline models by 2% in the nearest
neighbour ranking.

Original language	English
Pages	1222-1228
Number of pages	7
DOIs	https://doi.org/10.26615/978-954-452-056-4_140
Publication status	Published - 2-Sept-2019
Event	Recent Advances in Natural Language Processing 2019 - Varna, Bulgaria Duration: 2-Sept-2019 → 4-Sept-2019 http://lml.bas.bg/ranlp2019/start.php

Conference

Conference	Recent Advances in Natural Language Processing 2019
Abbreviated title	RANLP 2019
Country/Territory	Bulgaria
City	Varna
Period	02/09/2019 → 04/09/2019
Internet address	http://lml.bas.bg/ranlp2019/start.php

Access to Document

10.26615/978-954-452-056-4_140Licence: CC BY

Cross-Lingual Word Embeddings for Morphologically Rich LanguagesFinal publisher's version, 259 KBLicence: CC BY

Handle.net

Persistent link

Cite this

@conference{263ecf3fb80740b2b44e3a260bf5d32f,

title = "Cross-Lingual Word Embeddings for Morphologically Rich Languages",

abstract = "Cross-lingual word embedding models learna shared vector space for two or more lan-guages so that words with similar meaningare represented by similar vectors regardlessof their language. Although the existing mod-els achieve high performance on pairs of mor-phologically simple languages, they performvery poorly on morphologically rich languagessuch as Turkish and Finnish. In this pa-per, we propose a morpheme-based model inorder to increase the performance of cross-lingual word embeddings on morphologicallyrich languages. Our model includes a sim-ple extension which enables us to exploit mor-phemes for cross-lingual mapping. We ap-plied our model for the Turkish-Finnish lan-guage pair on the bilingual word translationtask. Results show that our model outper-forms the baseline models by 2% in the nearestneighbour ranking.",

author = "Ahmet {\"U}st{\"u}n and Gosse Bouma and {Noord, van}, Gerardus",

year = "2019",

month = sep,

day = "2",

doi = "10.26615/978-954-452-056-4_140",

language = "English",

pages = "1222--1228",

note = "Recent Advances in Natural Language Processing 2019, RANLP 2019 ; Conference date: 02-09-2019 Through 04-09-2019",

url = "http://lml.bas.bg/ranlp2019/start.php",

}

TY - CONF

T1 - Cross-Lingual Word Embeddings for Morphologically Rich Languages

AU - Üstün, Ahmet

AU - Bouma, Gosse

AU - Noord, van, Gerardus

PY - 2019/9/2

Y1 - 2019/9/2

N2 - Cross-lingual word embedding models learna shared vector space for two or more lan-guages so that words with similar meaningare represented by similar vectors regardlessof their language. Although the existing mod-els achieve high performance on pairs of mor-phologically simple languages, they performvery poorly on morphologically rich languagessuch as Turkish and Finnish. In this pa-per, we propose a morpheme-based model inorder to increase the performance of cross-lingual word embeddings on morphologicallyrich languages. Our model includes a sim-ple extension which enables us to exploit mor-phemes for cross-lingual mapping. We ap-plied our model for the Turkish-Finnish lan-guage pair on the bilingual word translationtask. Results show that our model outper-forms the baseline models by 2% in the nearestneighbour ranking.

AB - Cross-lingual word embedding models learna shared vector space for two or more lan-guages so that words with similar meaningare represented by similar vectors regardlessof their language. Although the existing mod-els achieve high performance on pairs of mor-phologically simple languages, they performvery poorly on morphologically rich languagessuch as Turkish and Finnish. In this pa-per, we propose a morpheme-based model inorder to increase the performance of cross-lingual word embeddings on morphologicallyrich languages. Our model includes a sim-ple extension which enables us to exploit mor-phemes for cross-lingual mapping. We ap-plied our model for the Turkish-Finnish lan-guage pair on the bilingual word translationtask. Results show that our model outper-forms the baseline models by 2% in the nearestneighbour ranking.

U2 - 10.26615/978-954-452-056-4_140

DO - 10.26615/978-954-452-056-4_140

M3 - Paper

SP - 1222

EP - 1228

T2 - Recent Advances in Natural Language Processing 2019

Y2 - 2 September 2019 through 4 September 2019

ER -