English

Learning Joint Semantic Parsers from Disjoint Data

Computation and Language 2018-04-18 v1

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.

Keywords

Cite

@article{arxiv.1804.05990,
  title  = {Learning Joint Semantic Parsers from Disjoint Data},
  author = {Hao Peng and Sam Thomson and Swabha Swayamdipta and Noah A. Smith},
  journal= {arXiv preprint arXiv:1804.05990},
  year   = {2018}
}

Comments

NAACL 2018

R2 v1 2026-06-23T01:25:44.738Z