Syntax-aware Neural Semantic Role Labeling with Supertags
Abstract
We introduce a new syntax-aware model for dependency-based semantic role labeling that outperforms syntax-agnostic models for English and Spanish. We use a BiLSTM to tag the text with supertags extracted from dependency parses, and we feed these supertags, along with words and parts of speech, into a deep highway BiLSTM for semantic role labeling. Our model combines the strengths of earlier models that performed SRL on the basis of a full dependency parse with more recent models that use no syntactic information at all. Our local and non-ensemble model achieves state-of-the-art performance on the CoNLL 09 English and Spanish datasets. SRL models benefit from syntactic information, and we show that supertagging is a simple, powerful, and robust way to incorporate syntax into a neural SRL system.
Keywords
Cite
@article{arxiv.1903.05260,
title = {Syntax-aware Neural Semantic Role Labeling with Supertags},
author = {Jungo Kasai and Dan Friedman and Robert Frank and Dragomir Radev and Owen Rambow},
journal= {arXiv preprint arXiv:1903.05260},
year = {2019}
}
Comments
NAACL 2019, Added Spanish ELMo results