Evaluating a Deterministic Shift-Reduce Neural Parser for Constituent Parsing

Hao Zhou, Yue Zhang, Shujian Huang, Xin-Yu Dai, Jiajun Chen


Abstract
Greedy transition-based parsers are appealing for their very fast speed, with reasonably high accuracies. In this paper, we build a fast shift-reduce neural constituent parser by using a neural network to make local decisions. One challenge to the parsing speed is the large hidden and output layer sizes caused by the number of constituent labels and branching options. We speed up the parser by using a hierarchical output layer, inspired by the hierarchical log-bilinear neural language model. In standard WSJ experiments, the neural parser achieves an almost 2.4 time speed up (320 sen/sec) compared to a non-hierarchical baseline without significant accuracy loss (89.06 vs 89.13 F-score).
Anthology ID:
L16-1104
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
659–663
Language:
URL:
https://aclanthology.org/L16-1104
DOI:
Bibkey:
Cite (ACL):
Hao Zhou, Yue Zhang, Shujian Huang, Xin-Yu Dai, and Jiajun Chen. 2016. Evaluating a Deterministic Shift-Reduce Neural Parser for Constituent Parsing. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 659–663, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Evaluating a Deterministic Shift-Reduce Neural Parser for Constituent Parsing (Zhou et al., LREC 2016)
Copy Citation:
PDF:
https://aclanthology.org/L16-1104.pdf
Data
Penn Treebank