Easy-First Dependency Parsing with Hierarchical Tree LSTMs

Eliyahu Kiperwasser, Yoav Goldberg


Abstract
We suggest a compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders. To demonstrate its effectiveness, we use the representation as the backbone of a greedy, bottom-up dependency parser, achieving very strong accuracies for English and Chinese, without relying on external word embeddings. The parser’s implementation is available for download at the first author’s webpage.
Anthology ID:
Q16-1032
Volume:
Transactions of the Association for Computational Linguistics, Volume 4
Month:
Year:
2016
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
445–461
Language:
URL:
https://aclanthology.org/Q16-1032
DOI:
10.1162/tacl_a_00110
Bibkey:
Cite (ACL):
Eliyahu Kiperwasser and Yoav Goldberg. 2016. Easy-First Dependency Parsing with Hierarchical Tree LSTMs. Transactions of the Association for Computational Linguistics, 4:445–461.
Cite (Informal):
Easy-First Dependency Parsing with Hierarchical Tree LSTMs (Kiperwasser & Goldberg, TACL 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/Q16-1032.pdf
Video:
 https://preview.aclanthology.org/ml4al-ingestion/Q16-1032.mp4