End-to-end Graph-based TAG Parsing with Neural Networks
Abstract
We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Our best end-to-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-the-art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.
Keywords
Cite
@article{arxiv.1804.06610,
title = {End-to-end Graph-based TAG Parsing with Neural Networks},
author = {Jungo Kasai and Robert Frank and Pauli Xu and William Merrill and Owen Rambow},
journal= {arXiv preprint arXiv:1804.06610},
year = {2018}
}
Comments
NAACL 2018