Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
Computation and Language
2018-07-06 v2 Artificial Intelligence
Abstract
We present a transition-based parser that jointly produces syntactic and semantic dependencies. It learns a representation of the entire algorithm state, using stack long short-term memories. Our greedy inference algorithm has linear time, including feature extraction. On the CoNLL 2008--9 English shared tasks, we obtain the best published parsing performance among models that jointly learn syntax and semantics.
Cite
@article{arxiv.1606.08954,
title = {Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs},
author = {Swabha Swayamdipta and Miguel Ballesteros and Chris Dyer and Noah A. Smith},
journal= {arXiv preprint arXiv:1606.08954},
year = {2018}
}
Comments
Proceedings of CoNLL 2016; 13 pages, 5 figures