Header

UZH-Logo

Maintenance Infos

UZH at CoNLL-SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection


Makarov, Peter; Clematide, Simon (2018). UZH at CoNLL-SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection. In: CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection, Brussels, Belgium, 31 October 2018 - 31 October 2018, 69-75.

Abstract

This paper presents the submissions by the University of Zurich to the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection. Our system is based on the prior work on neural transitionbased transduction (Makarov and Clematide, 2018b; Aharoni and Goldberg, 2017). Unlike the prior work, we train the model in a fully end-to-end fashion—without the need for an external character aligner—within the framework of imitation learning. In the type-level morphological inflection generation challenge (Task I), our five-strong ensemble outperforms all competitors in all three data-size settings. In the token-level inflection generation challenge (Task II), our single model achieves the best results on three out of four sub-tasks that we have participated in.

Abstract

This paper presents the submissions by the University of Zurich to the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection. Our system is based on the prior work on neural transitionbased transduction (Makarov and Clematide, 2018b; Aharoni and Goldberg, 2017). Unlike the prior work, we train the model in a fully end-to-end fashion—without the need for an external character aligner—within the framework of imitation learning. In the type-level morphological inflection generation challenge (Task I), our five-strong ensemble outperforms all competitors in all three data-size settings. In the token-level inflection generation challenge (Task II), our single model achieves the best results on three out of four sub-tasks that we have participated in.

Statistics

Citations

Downloads

11 downloads since deposited on 22 Feb 2019
11 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Uncontrolled Keywords:Morphology; Machine Learning; Neural Networks
Language:English
Event End Date:31 October 2018
Deposited On:22 Feb 2019 08:34
Last Modified:30 Oct 2019 08:13
Publisher:Association for Computational Linguistics
Number of Pages:-143
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:http://www.aclweb.org/anthology/K18-3008
Project Information:
  • : FunderFP7
  • : Grant ID338875
  • : Project TitlePolitical Conflict in Europe in the Shadow of the Great Recession
  • : FunderSNSF
  • : Grant IDCRSII5_173719
  • : Project TitleMedia Monitoring of the Past

Download

Green Open Access

Download PDF  'UZH at CoNLL-SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 216kB
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)