Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis

Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao, Weiwei Sun, Xiaojun Wan


Abstract
We present experiments for cross-domain semantic dependency analysis with a neural Maximum Subgraph parser. Our parser targets 1-endpoint-crossing, pagenumber-2 graphs which are a good fit to semantic dependency graphs, and utilizes an efficient dynamic programming algorithm for decoding. For disambiguation, the parser associates words with BiLSTM vectors and utilizes these vectors to assign scores to candidate dependencies. We conduct experiments on the data sets from SemEval 2015 as well as Chinese CCGBank. Our parser achieves very competitive results for both English and Chinese. To improve the parsing performance on cross-domain texts, we propose a data-oriented method to explore the linguistic generality encoded in English Resource Grammar, which is a precisionoriented, hand-crafted HPSG grammar, in an implicit way. Experiments demonstrate the effectiveness of our data-oriented method across a wide range of conditions.
Anthology ID:
K18-1054
Volume:
Proceedings of the 22nd Conference on Computational Natural Language Learning
Month:
October
Year:
2018
Address:
Brussels, Belgium
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
562–572
Language:
URL:
https://aclanthology.org/K18-1054
DOI:
10.18653/v1/K18-1054
Bibkey:
Cite (ACL):
Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao, Weiwei Sun, and Xiaojun Wan. 2018. Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 562–572, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis (Chen et al., CoNLL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/K18-1054.pdf
Code
 draplater/msg-parser
Data
Penn Treebank