Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
Semantic dependency parsing aims to identify semantic relationships between words in a sentence that form a graph. In this paper, we propose a second-order semantic dependency parser, which takes into consideration not only individual dependency edges but also interactions between pairs of edges. We show that second-order parsing can be approximated using mean field (MF) variational inference or loopy belief propagation (LBP). We can unfold both algorithms as recurrent layers of a neural network and therefore can train the parser in an end-to-end manner. Our experiments show that our approach achieves state-of-the-art performance.
PDF Abstract ACL 2019 PDF ACL 2019 AbstractCode
Datasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Semantic Dependency Parsing | DM | MFVI | In-domain | 94.0 | # 3 | |
Out-of-domain | 89.7 | # 3 | ||||
Semantic Dependency Parsing | PAS | MFVI | In-domain | 94.1 | # 3 | |
Out-of-domain | 91.3 | # 3 | ||||
Semantic Dependency Parsing | PSD | MFVI | In-domain | 81.4 | # 3 | |
Out-of-domain | 79.6 | # 3 |