Unsupervised Recurrent Neural Network Grammars

Yoon Kim, Alexander Rush, Lei Yu, Adhiguna Kuncoro, Chris Dyer, Gábor Melis


Abstract
Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order. Supervised RNNGs achieve strong language modeling and parsing performance, but require an annotated corpus of parse trees. In this work, we experiment with unsupervised learning of RNNGs. Since directly marginalizing over the space of latent trees is intractable, we instead apply amortized variational inference. To maximize the evidence lower bound, we develop an inference network parameterized as a neural CRF constituency parser. On language modeling, unsupervised RNNGs perform as well their supervised counterparts on benchmarks in English and Chinese. On constituency grammar induction, they are competitive with recent neural language models that induce tree structures from words through attention mechanisms.
Anthology ID:
N19-1114
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1105–1117
Language:
URL:
https://aclanthology.org/N19-1114
DOI:
10.18653/v1/N19-1114
Bibkey:
Cite (ACL):
Yoon Kim, Alexander Rush, Lei Yu, Adhiguna Kuncoro, Chris Dyer, and Gábor Melis. 2019. Unsupervised Recurrent Neural Network Grammars. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1105–1117, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Recurrent Neural Network Grammars (Kim et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1114.pdf
Video:
 https://vimeo.com/364668925
Code
 harvardnlp/urnng
Data
Billion Word BenchmarkPenn Treebank