An Imitation Learning Approach to Unsupervised Parsing

Bowen Li, Lili Mou, Frank Keller


Abstract
Recently, there has been an increasing interest in unsupervised parsers that optimize semantically oriented objectives, typically using reinforcement learning. Unfortunately, the learned trees often do not match actual syntax trees well. Shen et al. (2018) propose a structured attention mechanism for language modeling (PRPN), which induces better syntactic structures but relies on ad hoc heuristics. Also, their model lacks interpretability as it is not grounded in parsing actions. In our work, we propose an imitation learning approach to unsupervised parsing, where we transfer the syntactic knowledge induced by PRPN to a Tree-LSTM model with discrete parsing actions. Its policy is then refined by Gumbel-Softmax training towards a semantically oriented objective. We evaluate our approach on the All Natural Language Inference dataset and show that it achieves a new state of the art in terms of parsing F-score, outperforming our base models, including PRPN.
Anthology ID:
P19-1338
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3485–3492
Language:
URL:
https://aclanthology.org/P19-1338
DOI:
10.18653/v1/P19-1338
Bibkey:
Cite (ACL):
Bowen Li, Lili Mou, and Frank Keller. 2019. An Imitation Learning Approach to Unsupervised Parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3485–3492, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
An Imitation Learning Approach to Unsupervised Parsing (Li et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-dup-bibkey/P19-1338.pdf
Video:
 https://preview.aclanthology.org/fix-dup-bibkey/P19-1338.mp4
Code
 libowen2121/Imitation-Learning-for-Unsup-Parsing
Data
MultiNLI