The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection

Katharina Kann, Stanislas Lauly, Kyunghyun Cho

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

Abstract

This paper describes the NYU submission to the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. Our system participates in the low-resource setting of Task 2, track 2, i.e., it predicts morphologically inflected forms in context: given a lemma and a context sentence, it produces a form of the lemma which might be used at an indicated position in the sentence. It is based on the standard attention-based LSTM encoder-decoder model, but makes use of multiple encoders to process all parts of the context as well as the lemma. In the official shared task evaluation, our system obtains the second best results out of 5 submissions for the competition it entered and strongly outperforms the official baseline.

Original languageEnglish (US)
Title of host publicationCoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task
Subtitle of host publicationUniversal Morphological Reinflection
PublisherAssociation for Computational Linguistics (ACL)
Pages58-63
Number of pages6
ISBN (Electronic)9781948087834
StatePublished - Jan 1 2018
Event2018 CoNLL-SIGMORPHON Shared Task: Universal Morphological Reinflection, CoNLL 2018 - Brussels, Belgium
Duration: Oct 31 2018 → …

Publication series

NameCoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

Conference

Conference2018 CoNLL-SIGMORPHON Shared Task: Universal Morphological Reinflection, CoNLL 2018
CountryBelgium
CityBrussels
Period10/31/18 → …

Fingerprint

evaluation
resources

ASJC Scopus subject areas

  • Linguistics and Language
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Kann, K., Lauly, S., & Cho, K. (2018). The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. In CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection (pp. 58-63). (CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection). Association for Computational Linguistics (ACL).

The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. / Kann, Katharina; Lauly, Stanislas; Cho, Kyunghyun.

CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. Association for Computational Linguistics (ACL), 2018. p. 58-63 (CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection).

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

Kann, K, Lauly, S & Cho, K 2018, The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. in CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection, Association for Computational Linguistics (ACL), pp. 58-63, 2018 CoNLL-SIGMORPHON Shared Task: Universal Morphological Reinflection, CoNLL 2018, Brussels, Belgium, 10/31/18.
Kann K, Lauly S, Cho K. The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. In CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. Association for Computational Linguistics (ACL). 2018. p. 58-63. (CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection).
Kann, Katharina ; Lauly, Stanislas ; Cho, Kyunghyun. / The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. Association for Computational Linguistics (ACL), 2018. pp. 58-63 (CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection).
@inproceedings{17d1e92d28d045d5a0bb0edc00db5e2d,
title = "The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection",
abstract = "This paper describes the NYU submission to the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. Our system participates in the low-resource setting of Task 2, track 2, i.e., it predicts morphologically inflected forms in context: given a lemma and a context sentence, it produces a form of the lemma which might be used at an indicated position in the sentence. It is based on the standard attention-based LSTM encoder-decoder model, but makes use of multiple encoders to process all parts of the context as well as the lemma. In the official shared task evaluation, our system obtains the second best results out of 5 submissions for the competition it entered and strongly outperforms the official baseline.",
author = "Katharina Kann and Stanislas Lauly and Kyunghyun Cho",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
series = "CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection",
publisher = "Association for Computational Linguistics (ACL)",
pages = "58--63",
booktitle = "CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task",

}

TY - GEN

T1 - The NYU system for the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection

AU - Kann, Katharina

AU - Lauly, Stanislas

AU - Cho, Kyunghyun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper describes the NYU submission to the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. Our system participates in the low-resource setting of Task 2, track 2, i.e., it predicts morphologically inflected forms in context: given a lemma and a context sentence, it produces a form of the lemma which might be used at an indicated position in the sentence. It is based on the standard attention-based LSTM encoder-decoder model, but makes use of multiple encoders to process all parts of the context as well as the lemma. In the official shared task evaluation, our system obtains the second best results out of 5 submissions for the competition it entered and strongly outperforms the official baseline.

AB - This paper describes the NYU submission to the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. Our system participates in the low-resource setting of Task 2, track 2, i.e., it predicts morphologically inflected forms in context: given a lemma and a context sentence, it produces a form of the lemma which might be used at an indicated position in the sentence. It is based on the standard attention-based LSTM encoder-decoder model, but makes use of multiple encoders to process all parts of the context as well as the lemma. In the official shared task evaluation, our system obtains the second best results out of 5 submissions for the competition it entered and strongly outperforms the official baseline.

UR - http://www.scopus.com/inward/record.url?scp=85072901993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072901993&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85072901993

T3 - CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

SP - 58

EP - 63

BT - CoNLL 2018 - Proceedings of the CoNLL-SIGMORPHON 2018 Shared Task

PB - Association for Computational Linguistics (ACL)

ER -