Seq2seq Dependency Parsing

Zuchao Li, Jiaxun Cai, Shexia He, Hai Zhao


Abstract
This paper presents a sequence to sequence (seq2seq) dependency parser by directly predicting the relative position of head for each given word, which therefore results in a truly end-to-end seq2seq dependency parser for the first time. Enjoying the advantage of seq2seq modeling, we enrich a series of embedding enhancement, including firstly introduced subword and node2vec augmentation. Meanwhile, we propose a beam search decoder with tree constraint and subroot decomposition over the sequence to furthermore enhance our seq2seq parser. Our parser is evaluated on benchmark treebanks, being on par with the state-of-the-art parsers by achieving 94.11% UAS on PTB and 88.78% UAS on CTB, respectively.
Anthology ID:
C18-1271
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3203–3214
Language:
URL:
https://aclanthology.org/C18-1271
DOI:
Bibkey:
Cite (ACL):
Zuchao Li, Jiaxun Cai, Shexia He, and Hai Zhao. 2018. Seq2seq Dependency Parsing. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3203–3214, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Seq2seq Dependency Parsing (Li et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/C18-1271.pdf
Code
 bcmi220/seq2seq_parser +  additional community code