Abstract
We present a simple and effective scheme for dependency parsing which is based on bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector representing the token in its sentential context, and feature vectors are constructed by concatenating a few BiLSTM vectors. The BiLSTM is trained jointly with the parser objective, resulting in very effective feature extractors for parsing. We demonstrate the effectiveness of the approach by applying it to a greedy transition-based parser as well as to a globally optimized graph-based parser. The resulting parsers have very simple architectures, and match or surpass the state-of-the-art accuracies on English and Chinese.- Anthology ID:
- Q16-1023
- 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:
- 313–327
- Language:
- URL:
- https://aclanthology.org/Q16-1023
- DOI:
- 10.1162/tacl_a_00101
- Cite (ACL):
- Eliyahu Kiperwasser and Yoav Goldberg. 2016. Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations. Transactions of the Association for Computational Linguistics, 4:313–327.
- Cite (Informal):
- Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations (Kiperwasser & Goldberg, TACL 2016)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/Q16-1023.pdf
- Code
- elikip/bist-parser
- Data
- Penn Treebank