Character-Aware Neural Morphological Disambiguation

Alymzhan Toleu, Gulmira Tolegen, Aibek Makazhanov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We develop a language-independent, deep learning-based approach to the task of morphological disambiguation. Guided by the intuition that the correct analysis should be ``most similar'' to the context, we propose dense representations for morphological analyses and surface context and a simple yet effective way of combining the two to perform disambiguation. Our approach improves on the language-dependent state of the art for two agglutinative languages (Turkish and Kazakh) and can be potentially applied to other morphologically complex languages.
Original languageUndefined/Unknown
Title of host publicationProceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Place of PublicationVancouver, Canada
PublisherAssociation for Computational Linguistics (ACL)
Pages666-671
Number of pages6
Publication statusPublished - Jul 1 2017

Cite this

Toleu, A., Tolegen, G., & Makazhanov, A. (2017). Character-Aware Neural Morphological Disambiguation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 666-671). Vancouver, Canada: Association for Computational Linguistics (ACL).

Character-Aware Neural Morphological Disambiguation. / Toleu, Alymzhan; Tolegen, Gulmira; Makazhanov, Aibek.

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Vancouver, Canada : Association for Computational Linguistics (ACL), 2017. p. 666-671.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Toleu, A, Tolegen, G & Makazhanov, A 2017, Character-Aware Neural Morphological Disambiguation. in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics (ACL), Vancouver, Canada, pp. 666-671.
Toleu A, Tolegen G, Makazhanov A. Character-Aware Neural Morphological Disambiguation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Vancouver, Canada: Association for Computational Linguistics (ACL). 2017. p. 666-671
Toleu, Alymzhan ; Tolegen, Gulmira ; Makazhanov, Aibek. / Character-Aware Neural Morphological Disambiguation. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Vancouver, Canada : Association for Computational Linguistics (ACL), 2017. pp. 666-671
@inproceedings{cc697389d92c4e5a8d2ef668f5c68d22,
title = "Character-Aware Neural Morphological Disambiguation",
abstract = "We develop a language-independent, deep learning-based approach to the task of morphological disambiguation. Guided by the intuition that the correct analysis should be ``most similar'' to the context, we propose dense representations for morphological analyses and surface context and a simple yet effective way of combining the two to perform disambiguation. Our approach improves on the language-dependent state of the art for two agglutinative languages (Turkish and Kazakh) and can be potentially applied to other morphologically complex languages.",
author = "Alymzhan Toleu and Gulmira Tolegen and Aibek Makazhanov",
year = "2017",
month = "7",
day = "1",
language = "Undefined/Unknown",
pages = "666--671",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Character-Aware Neural Morphological Disambiguation

AU - Toleu, Alymzhan

AU - Tolegen, Gulmira

AU - Makazhanov, Aibek

PY - 2017/7/1

Y1 - 2017/7/1

N2 - We develop a language-independent, deep learning-based approach to the task of morphological disambiguation. Guided by the intuition that the correct analysis should be ``most similar'' to the context, we propose dense representations for morphological analyses and surface context and a simple yet effective way of combining the two to perform disambiguation. Our approach improves on the language-dependent state of the art for two agglutinative languages (Turkish and Kazakh) and can be potentially applied to other morphologically complex languages.

AB - We develop a language-independent, deep learning-based approach to the task of morphological disambiguation. Guided by the intuition that the correct analysis should be ``most similar'' to the context, we propose dense representations for morphological analyses and surface context and a simple yet effective way of combining the two to perform disambiguation. Our approach improves on the language-dependent state of the art for two agglutinative languages (Turkish and Kazakh) and can be potentially applied to other morphologically complex languages.

M3 - Conference contribution

SP - 666

EP - 671

BT - Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

PB - Association for Computational Linguistics (ACL)

CY - Vancouver, Canada

ER -