ITU

Lexical Resources for Low-Resource PoS Tagging in Neural Times

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Standard

Lexical Resources for Low-Resource PoS Tagging in Neural Times. / Plank, Barbara; Klerke, Sigrid.

Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) . Association for Computational Linguistics, 2019. p. 25–34 (NEALT (Northern European Association of Language Technology) Proceedings Series).

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Harvard

Plank, B & Klerke, S 2019, Lexical Resources for Low-Resource PoS Tagging in Neural Times. in Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) . Association for Computational Linguistics, NEALT (Northern European Association of Language Technology) Proceedings Series, pp. 25–34.

APA

Plank, B., & Klerke, S. (2019). Lexical Resources for Low-Resource PoS Tagging in Neural Times. In Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) (pp. 25–34). Association for Computational Linguistics. NEALT (Northern European Association of Language Technology) Proceedings Series

Vancouver

Plank B, Klerke S. Lexical Resources for Low-Resource PoS Tagging in Neural Times. In Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) . Association for Computational Linguistics. 2019. p. 25–34. (NEALT (Northern European Association of Language Technology) Proceedings Series).

Author

Plank, Barbara ; Klerke, Sigrid. / Lexical Resources for Low-Resource PoS Tagging in Neural Times. Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19) . Association for Computational Linguistics, 2019. pp. 25–34 (NEALT (Northern European Association of Language Technology) Proceedings Series).

Bibtex

@inproceedings{aad5e6ca1ffc4dcfb01618dec3f3d679,
title = "Lexical Resources for Low-Resource PoS Tagging in Neural Times",
abstract = "More and more evidence is appearing that integrating symbolic lexical knowledge into neural models aids learning. This contrasts the widely-held belief that neural networks largely learn their own feature representations. For example, recent work has shown benefits of integrating lexicons to aid cross-lingual part-of-speech (PoS). However, little is known on how complementary such additional information is, and to what extent improvements depend on the coverage and quality of these external resources. This paper seeks to fill this gap by providing a thorough analysis on the contributions of lexical resources for cross-lingual PoS tagging in neural times.",
author = "Barbara Plank and Sigrid Klerke",
year = "2019",
language = "English",
series = "NEALT (Northern European Association of Language Technology) Proceedings Series",
pages = "25–34",
booktitle = "Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa{\textquoteright}19)",
publisher = "Association for Computational Linguistics",
address = "United States",

}

RIS

TY - GEN

T1 - Lexical Resources for Low-Resource PoS Tagging in Neural Times

AU - Plank, Barbara

AU - Klerke, Sigrid

PY - 2019

Y1 - 2019

N2 - More and more evidence is appearing that integrating symbolic lexical knowledge into neural models aids learning. This contrasts the widely-held belief that neural networks largely learn their own feature representations. For example, recent work has shown benefits of integrating lexicons to aid cross-lingual part-of-speech (PoS). However, little is known on how complementary such additional information is, and to what extent improvements depend on the coverage and quality of these external resources. This paper seeks to fill this gap by providing a thorough analysis on the contributions of lexical resources for cross-lingual PoS tagging in neural times.

AB - More and more evidence is appearing that integrating symbolic lexical knowledge into neural models aids learning. This contrasts the widely-held belief that neural networks largely learn their own feature representations. For example, recent work has shown benefits of integrating lexicons to aid cross-lingual part-of-speech (PoS). However, little is known on how complementary such additional information is, and to what extent improvements depend on the coverage and quality of these external resources. This paper seeks to fill this gap by providing a thorough analysis on the contributions of lexical resources for cross-lingual PoS tagging in neural times.

UR - https://www.aclweb.org/anthology/W19-6103.pdf

M3 - Article in proceedings

T3 - NEALT (Northern European Association of Language Technology) Proceedings Series

SP - 25

EP - 34

BT - Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19)

PB - Association for Computational Linguistics

ER -

ID: 84271593