A Span Selection Model for Semantic Role Labeling

EMNLP 2018  ·  Hiroki Ouchi, Hiroyuki Shindo, Yuji Matsumoto ·

We present a simple and accurate span-based model for semantic role labeling (SRL). Our model directly takes into account all possible argument spans and scores them for each label. At decoding time, we greedily select higher scoring labeled spans. One advantage of our model is to allow us to design and use span-level features, that are difficult to use in token-based BIO tagging approaches. Experimental results demonstrate that our ensemble model achieves the state-of-the-art results, 87.4 F1 and 87.0 F1 on the CoNLL-2005 and 2012 datasets, respectively.

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Role Labeling CoNLL 2005 BiLSTM-Span (Ensemble, predicates given) F1 88.5 # 7
Compare
Semantic Role Labeling CoNLL 2005 BiLSTM-Span F1 87.6 # 10
Compare
Semantic Role Labeling OntoNotes BiLSTM-Span (Ensemble) F1 87.0 # 8
Compare
Semantic Role Labeling OntoNotes BiLSTM-Span F1 86.2 # 9
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