Simpler but More Accurate Semantic Dependency Parsing

ACL 2018  ·  Timothy Dozat, Christopher D. Manning ·

While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations. We extend the LSTM-based syntactic parser of Dozat and Manning (2017) to train on and generate these graph structures. The resulting system on its own achieves state-of-the-art performance, beating the previous, substantially more complex state-of-the-art system by 0.6% labeled F1. Adding linguistically richer input representations pushes the margin even higher, allowing us to beat it by 1.9% labeled F1.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Results from the Paper
Edit

Ranked #4 on Semantic Dependency Parsing on DM

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Dependency Parsing DM Dozat et al. (2018) In-domain 93.7 # 4
Compare
Out-of-domain 88.9 # 4
Compare
Semantic Dependency Parsing PAS Dozat et al. (2018) In-domain 93.9 # 4
Compare
Out-of-domain 90.6 # 4
Compare
Semantic Dependency Parsing PSD Dozat et al. (2018) In-domain 81.0 # 4
Compare
Out-of-domain 79.4 # 4
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy