Learning Joint Semantic Parsers from Disjoint Data

Hao Peng, Sam Thomson, Swabha Swayamdipta, Noah A. Smith
4/17/2018
cs.CL

Official code: Noahs-ARK/NeurboParser (71 stars, LGPL-3.0, last commit 2020-09-18).

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.

View on arXivView PDF

Code Implementations(1)

Noahs-ARK/NeurboParserOfficial100%
LGPL-3.0

A neural TurboSemanticParser as described in "Deep Multitask Learning for Semantic Dependency Parsing", Peng et al., ACL 2017.

7118C, C++Apr 20, 20176 years agoLGPL-3.0

Cite this paper

@article{peng2018learning,
  title  = {Learning Joint Semantic Parsers from Disjoint Data},
  author = {Hao Peng and Sam Thomson and Swabha Swayamdipta and Noah A. Smith},
  year   = {2018},
  eprint = {1804.05990},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1804.05990}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1804.05990.svg)](https://codeofpaper.com/paper/1804.05990)

Discussion