Improving AMR parsing by exploiting the dependency parsing as an auxiliary task
| Autor: | Junsheng Zhou, Bin Li, Weiguang Qu, Yunfei Long, Huilin Zhong, Taizhong Wu, Yanhui Gu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Parsing
Computer Networks and Communications Computer science business.industry 020207 software engineering Data_CODINGANDINFORMATIONTHEORY 02 engineering and technology computer.software_genre Semantics Directed acyclic graph Syntax TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES Hardware and Architecture Dependency grammar 0202 electrical engineering electronic engineering information engineering Media Technology Graph (abstract data type) Artificial intelligence business computer Software Sentence Natural language processing |
| Zdroj: | Multimedia Tools and Applications. 80:30827-30838 |
| ISSN: | 1573-7721 1380-7501 |
| DOI: | 10.1007/s11042-020-09967-3 |
| Popis: | meaning representations (AMRs) represent sentence semantics as rooted labeled directed acyclic graphs. Though there is a strong correlation between the AMR graph of a sentence and its corresponding dependency tree, the recent neural network AMR parsers do neglect the exploitation of dependency structure information. In this paper, we explore a novel approach to exploiting dependency structures for AMR parsing. Unlike traditional pipeline models, we treat dependency parsing as an auxiliary task for AMR parsing under the multi-task learning framework by sharing neural network parameters and selectively extracting syntactic representation by the attention mechanism. Particularly, to balance the gradients and focus on the AMR parsing task, we present a new dynamical weighting scheme in the loss function. The experimental results on the LDC2015E86 and LDC2017T10 dataset show that our dependency-auxiliary AMR parser significantly outperforms the baseline and its pipeline counterpart, and demonstrate that the neural AMR parsers can be greatly boosted with the help of effective methods of integrating syntax. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink