Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs

Miguel Ballesteros, Chris Dyer, Noah A. Smith


Anthology ID:
D15-1041
Volume:
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2015
Address:
Lisbon, Portugal
Editors:
Lluís Màrquez, Chris Callison-Burch, Jian Su
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
349–359
Language:
URL:
https://aclanthology.org/D15-1041
DOI:
10.18653/v1/D15-1041
Bibkey:
Cite (ACL):
Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2015. Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 349–359, Lisbon, Portugal. Association for Computational Linguistics.
Cite (Informal):
Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs (Ballesteros et al., EMNLP 2015)
Copy Citation:
PDF:
https://aclanthology.org/D15-1041.pdf
Video:
 https://aclanthology.org/D15-1041.mp4
Code
 clab/lstm-parser
Data
Penn Treebank