An Imitation Learning Approach to Unsupervised Parsing
Full Text: P19-1338.pdf
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.
Citation
B. Li, L. Mou, F. Keller. "An Imitation Learning Approach to Unsupervised Parsing". International Conference on Computational Linguistics and the Association for Computational Linguist, pp 3485–3492, July 2019.| Keywords: | |
| Category: | In Conference |
| Web Links: | doi |
| ACL |
BibTeX
@incollection{Li+al:ACL19,
author = {Bowen Li and Lili Mou and Frank Keller},
title = {An Imitation Learning Approach to Unsupervised Parsing},
Pages = {3485–3492},
booktitle = {International Conference on Computational Linguistics and the
Association for Computational Linguist},
year = 2019,
}Last Updated: February 02, 2021Submitted by Sabina P
