Learning Joint Semantic Parsers from Disjoint Data

ACL 2018

Learning Joint Semantic Parsers from Disjoint Data

Jan 21, 2021
|
30 views
|
Details
Abstract: We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle such "disjoint" data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly. Authors: Hao Peng, Sam Thomson, Swabha Swayamdipta, Noah A. Smith (University of Washington, Carnegie Mellon University)

Comments
loading...