Imitation Learning for Neural Morphological String Transduction

Peter Makarov, Simon Clematide


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.
Anthology ID:
D18-1314
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2877–2882
Language:
URL:
https://aclanthology.org/D18-1314
DOI:
10.18653/v1/D18-1314
Bibkey:
Cite (ACL):
Peter Makarov and Simon Clematide. 2018. Imitation Learning for Neural Morphological String Transduction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2877–2882, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Imitation Learning for Neural Morphological String Transduction (Makarov & Clematide, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1314.pdf
Video:
 https://aclanthology.org/D18-1314.mp4
Code
 ZurichNLP/emnlp2018-imitation-learning-for-neural-morphology