Header

UZH-Logo

Maintenance Infos

Neural Transition-based String Transduction for Limited-Resource Setting in Morphology


Makarov, Peter; Clematide, Simon (2018). Neural Transition-based String Transduction for Limited-Resource Setting in Morphology. In: Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, New Mexico, USA, 20 August 2018 - 26 August 2018, 83-93.

Abstract

We present a neural transition-based model that uses a simple set of edit actions (copy, delete, insert) for morphological transduction tasks such as inflection generation, lemmatization, and reinflection. In a large-scale evaluation on four datasets and dozens of languages, our approach consistently outperforms state-of-the-art systems on low and medium training-set sizes and is competitive in the high-resource setting. Learning to apply a generic copy action enables our approach to generalize quickly from a few data points. We successfully leverage minimum risk training to compensate for the weaknesses of MLE parameter learning and neutralize the negative effects of training a pipeline with a separate character aligner.

Abstract

We present a neural transition-based model that uses a simple set of edit actions (copy, delete, insert) for morphological transduction tasks such as inflection generation, lemmatization, and reinflection. In a large-scale evaluation on four datasets and dozens of languages, our approach consistently outperforms state-of-the-art systems on low and medium training-set sizes and is competitive in the high-resource setting. Learning to apply a generic copy action enables our approach to generalize quickly from a few data points. We successfully leverage minimum risk training to compensate for the weaknesses of MLE parameter learning and neutralize the negative effects of training a pipeline with a separate character aligner.

Statistics

Downloads

7 downloads since deposited on 08 Feb 2019
7 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
Language:English
Event End Date:26 August 2018
Deposited On:08 Feb 2019 12:42
Last Modified:08 Feb 2019 12:42
Publisher:Association for Computational Linguistics
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:http://aclweb.org/anthology/C18-1008
Related URLs:https://github.com/ZurichNLP/coling2018-neural-transition-based-morphology
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
  • : Project Websitehttp://p3.snf.ch/project-173719

Download

Download PDF  'Neural Transition-based String Transduction for Limited-Resource Setting in Morphology'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 817kB
Licence: Creative Commons: Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)