Header

UZH-Logo

Maintenance Infos

Imitation Learning for Neural Morphological String Transduction


Makarov, Peter; Clematide, Simon (2018). Imitation Learning for Neural Morphological String Transduction. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October 2018 - 4 November 2018, 2877-2882.

Abstract

We employ imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization. Previous approaches to training this type of model either rely on an external character aligner for the production of gold action sequences, which results in a suboptimal model due to the unwarranted dependence on a single gold action sequence despite spurious ambiguity, or require warm starting with an MLE model. Our approach only requires a simple expert policy, eliminating the need for a character aligner or warm start. It also addresses familiar MLE training biases and leads to strong and state-of-the-art performance on several benchmarks.

Abstract

We employ imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization. Previous approaches to training this type of model either rely on an external character aligner for the production of gold action sequences, which results in a suboptimal model due to the unwarranted dependence on a single gold action sequence despite spurious ambiguity, or require warm starting with an MLE model. Our approach only requires a simple expert policy, eliminating the need for a character aligner or warm start. It also addresses familiar MLE training biases and leads to strong and state-of-the-art performance on several benchmarks.

Statistics

Downloads

17 downloads since deposited on 08 Feb 2019
17 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:4 November 2018
Deposited On:08 Feb 2019 12:44
Last Modified:25 Sep 2019 00:08
Publisher:Association for Computational Linguistics
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:http://www.aclweb.org/anthology/D18-1314
Related URLs:https://github.com/ZurichNLP/emnlp2018-imitation-learning-for-neural-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

Download

Green Open Access

Download PDF  'Imitation Learning for Neural Morphological String Transduction'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 490kB
Licence: Creative Commons: Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)