Dependency parsing of code-switching data with cross-lingual feature representations

Niko Partanen, KyungTae Lim, Michael Rießler, Thierry Poibeau

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Kuvaus

This paper describes the test of a dependency parsing method which is based
on bidirectional LSTM feature representations and multilingual word embedding,
and evaluates the results on mono- and multilingual data. The results are similar
in all cases, with a slightly better results achieved using multilingual data. The
languages under investigation are Komi-Zyrian and Russian. Examination of the
results by relation type shows that some language specific constructions are correctly recognized even when they appear in naturally occurring code-switching
data.
Alkuperäiskielienglanti
OtsikkoProceedings of the 4th International Workshop on Computational Linguistics for Uralic languages
Sivumäärä17
KustantajaThe Association for Computational Linguistics
Julkaisupäivä2018
Sivut1-17
TilaJulkaistu - 2018
Julkaistu ulkoisestiKyllä
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Workshop for Computational Linguistics of Uralic Languages - University of Helsinki, Department of Modern Languages, Helsinki, Suomi
Kesto: 8 tammikuuta 20189 tammikuuta 2018
Konferenssinumero: 4
http://blogs.helsinki.fi/language-technology/iwclul-2018/

Tieteenalat

  • 6121 Kielitieteet

Lainaa tätä

Partanen, N., Lim, K., Rießler, M., & Poibeau, T. (2018). Dependency parsing of code-switching data with cross-lingual feature representations. teoksessa Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages (Sivut 1-17). The Association for Computational Linguistics.
Partanen, Niko ; Lim, KyungTae ; Rießler, Michael ; Poibeau, Thierry. / Dependency parsing of code-switching data with cross-lingual feature representations. Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages. The Association for Computational Linguistics, 2018. Sivut 1-17
@inproceedings{176307ce827c48c7b9e74ec37dc7e693,
title = "Dependency parsing of code-switching data with cross-lingual feature representations",
abstract = "This paper describes the test of a dependency parsing method which is basedon bidirectional LSTM feature representations and multilingual word embedding,and evaluates the results on mono- and multilingual data. The results are similarin all cases, with a slightly better results achieved using multilingual data. Thelanguages under investigation are Komi-Zyrian and Russian. Examination of theresults by relation type shows that some language specific constructions are correctly recognized even when they appear in naturally occurring code-switchingdata.",
keywords = "6121 Languages",
author = "Niko Partanen and KyungTae Lim and Michael Rie{\ss}ler and Thierry Poibeau",
year = "2018",
language = "English",
pages = "1--17",
booktitle = "Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages",
publisher = "The Association for Computational Linguistics",
address = "United States",

}

Partanen, N, Lim, K, Rießler, M & Poibeau, T 2018, Dependency parsing of code-switching data with cross-lingual feature representations. julkaisussa Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages. The Association for Computational Linguistics, Sivut 1-17, International Workshop for Computational Linguistics of Uralic Languages, Helsinki, Suomi, 08/01/2018.

Dependency parsing of code-switching data with cross-lingual feature representations. / Partanen, Niko; Lim, KyungTae; Rießler, Michael; Poibeau, Thierry.

Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages. The Association for Computational Linguistics, 2018. s. 1-17.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

TY - GEN

T1 - Dependency parsing of code-switching data with cross-lingual feature representations

AU - Partanen, Niko

AU - Lim, KyungTae

AU - Rießler, Michael

AU - Poibeau, Thierry

PY - 2018

Y1 - 2018

N2 - This paper describes the test of a dependency parsing method which is basedon bidirectional LSTM feature representations and multilingual word embedding,and evaluates the results on mono- and multilingual data. The results are similarin all cases, with a slightly better results achieved using multilingual data. Thelanguages under investigation are Komi-Zyrian and Russian. Examination of theresults by relation type shows that some language specific constructions are correctly recognized even when they appear in naturally occurring code-switchingdata.

AB - This paper describes the test of a dependency parsing method which is basedon bidirectional LSTM feature representations and multilingual word embedding,and evaluates the results on mono- and multilingual data. The results are similarin all cases, with a slightly better results achieved using multilingual data. Thelanguages under investigation are Komi-Zyrian and Russian. Examination of theresults by relation type shows that some language specific constructions are correctly recognized even when they appear in naturally occurring code-switchingdata.

KW - 6121 Languages

M3 - Conference contribution

SP - 1

EP - 17

BT - Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages

PB - The Association for Computational Linguistics

ER -

Partanen N, Lim K, Rießler M, Poibeau T. Dependency parsing of code-switching data with cross-lingual feature representations. julkaisussa Proceedings of the 4th International Workshop on Computational Linguistics for Uralic languages. The Association for Computational Linguistics. 2018. s. 1-17