Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding

Yova Radoslavova Kementchedjhieva; Johannes Bjerva; Isabelle Augenstein

Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding

Yova Radoslavova Kementchedjhieva, Johannes Bjerva, Isabelle Augenstein

2 Citations (Scopus)

Abstract

This paper documents the Team Copenhagen system which placed first in the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection, Task 2 with an overall accuracy of 49.87. Task 2 focuses on morphological inflection in context: generating an inflected word form, given the lemma of the word and the context it occurs in. Previous SIGMORPHON shared tasks have focused on context-agnostic inflection—the “inflection in context” task was introduced this year. We approach this with an encoder-decoder architecture over character sequences with three core innovations, all contributing to an improvement in performance: (1) a wide context window; (2) a multi-task learning approach with the auxiliary task of MSD prediction; (3) training models in a multilingual fashion.

Original language	English
Title of host publication	Proceedings of the CoNLL SIGMORPHON 2018 Shared Task : Universal Morphological Reinflection
Publisher	Association for Computational Linguistics
Publication date	2018
Pages	93–98
Publication status	Published - 2018
Event	CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection - Brussels, Belgium Duration: 31 Oct 2018 → 31 Oct 2018

Workshop

Workshop	CoNLL–SIGMORPHON 2018 Shared Task
Country/Territory	Belgium
City	Brussels
Period	31/10/2018 → 31/10/2018

Cite this

Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding . / Kementchedjhieva, Yova Radoslavova; Bjerva, Johannes; Augenstein, Isabelle.
Proceedings of the CoNLL SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection . Association for Computational Linguistics, 2018. p. 93–98 .

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Kementchedjhieva, YR, Bjerva, J & Augenstein, I 2018, Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding . in Proceedings of the CoNLL SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection . Association for Computational Linguistics, pp. 93–98 , CoNLL–SIGMORPHON 2018 Shared Task, Brussels, Belgium, 31/10/2018.

@inproceedings{a6c4519f36684aa6af54fcc61ca4b439,

title = "Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding ",

abstract = "This paper documents the Team Copenhagen system which placed first in the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection, Task 2 with an overall accuracy of 49.87. Task 2 focuses on morphological inflection in context: generating an inflected word form, given the lemma of the word and the context it occurs in. Previous SIGMORPHON shared tasks have focused on context-agnostic inflection—the “inflection in context” task was introduced this year. We approach this with an encoder-decoder architecture over character sequences with three core innovations, all contributing to an improvement in performance: (1) a wide context window; (2) a multi-task learning approach with the auxiliary task of MSD prediction; (3) training models in a multilingual fashion.",

author = "Kementchedjhieva, {Yova Radoslavova} and Johannes Bjerva and Isabelle Augenstein",

year = "2018",

language = "English",

pages = "93–98 ",

booktitle = "Proceedings of the CoNLL SIGMORPHON 2018 Shared Task",

publisher = "Association for Computational Linguistics",

note = "CoNLL–SIGMORPHON 2018 Shared Task ; Conference date: 31-10-2018 Through 31-10-2018",

}

TY - GEN

T1 - Copenhagen at CoNLL–SIGMORPHON 2018

T2 - CoNLL–SIGMORPHON 2018 Shared Task

AU - Kementchedjhieva, Yova Radoslavova

AU - Bjerva, Johannes

AU - Augenstein, Isabelle

PY - 2018

Y1 - 2018

N2 - This paper documents the Team Copenhagen system which placed first in the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection, Task 2 with an overall accuracy of 49.87. Task 2 focuses on morphological inflection in context: generating an inflected word form, given the lemma of the word and the context it occurs in. Previous SIGMORPHON shared tasks have focused on context-agnostic inflection—the “inflection in context” task was introduced this year. We approach this with an encoder-decoder architecture over character sequences with three core innovations, all contributing to an improvement in performance: (1) a wide context window; (2) a multi-task learning approach with the auxiliary task of MSD prediction; (3) training models in a multilingual fashion.

AB - This paper documents the Team Copenhagen system which placed first in the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection, Task 2 with an overall accuracy of 49.87. Task 2 focuses on morphological inflection in context: generating an inflected word form, given the lemma of the word and the context it occurs in. Previous SIGMORPHON shared tasks have focused on context-agnostic inflection—the “inflection in context” task was introduced this year. We approach this with an encoder-decoder architecture over character sequences with three core innovations, all contributing to an improvement in performance: (1) a wide context window; (2) a multi-task learning approach with the auxiliary task of MSD prediction; (3) training models in a multilingual fashion.

M3 - Article in proceedings

SP - 93

EP - 98

BT - Proceedings of the CoNLL SIGMORPHON 2018 Shared Task

PB - Association for Computational Linguistics

Y2 - 31 October 2018 through 31 October 2018

ER -

Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding

Abstract

Workshop

Fingerprint

Cite this