HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding

Wanxiang Che, Longxu Dou, Yang Xu, Yuxuan Wang, Yijia Liu, Ting Liu


Abstract
This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. We extended the basic transition-based parser with two improvements: a) Efficient Training by realizing Stack LSTM parallel training; b) Effective Encoding via adopting deep contextualized word embeddings BERT. Generally, we proposed a unified pipeline to meaning representation parsing, including framework-specific transition-based parsers, BERT-enhanced word representation, and post-processing. In the final evaluation, our system was ranked first according to ALL-F1 (86.2%) and especially ranked first in UCCA framework (81.67%).
Anthology ID:
K19-2007
Volume:
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
Month:
November
Year:
2019
Address:
Hong Kong
Editors:
Stephan Oepen, Omri Abend, Jan Hajic, Daniel Hershcovich, Marco Kuhlmann, Tim O’Gorman, Nianwen Xue
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
76–85
Language:
URL:
https://aclanthology.org/K19-2007
DOI:
10.18653/v1/K19-2007
Bibkey:
Cite (ACL):
Wanxiang Che, Longxu Dou, Yang Xu, Yuxuan Wang, Yijia Liu, and Ting Liu. 2019. HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 76–85, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding (Che et al., CoNLL 2019)
Copy Citation:
PDF:
https://aclanthology.org/K19-2007.pdf
Attachment:
 K19-2007.Attachment.pdf
Data
CoNLL