An Imitation Learning Approach to Unsupervised Parsing

Bowen Li, Lili Mou, Frank Keller

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 the PRPN to a Tree-LSTM model with discrete parsing actions. Its policy is then refined by GumbelSoftmax 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 the PRPN.
Original languageEnglish
Title of host publicationAnnual Meeting of the Association for Computational Linguistics
Subtitle of host publicationShort Papers
EditorsAnna Korhonen, David Traum, Lluís Màrquez
Place of PublicationFlorence, Italy
PublisherAssociation for Computational Linguistics
Number of pages8
ISBN (Print)978-1-950737-48-2
Publication statusE-pub ahead of print - 2 Aug 2019
Event57th Annual Meeting of the Association for Computational Linguistics - Fortezza da Basso, Florence, Italy
Duration: 28 Jul 20192 Aug 2019
Conference number: 57


Conference57th Annual Meeting of the Association for Computational Linguistics
Abbreviated titleACL 2019
Internet address

Fingerprint Dive into the research topics of 'An Imitation Learning Approach to Unsupervised Parsing'. Together they form a unique fingerprint.

Cite this