A latent variable model of synchronous syntactic-semantic parsing for multiple languages

  • Authors:
  • Andrea Gesmundo;James Henderson;Paola Merlo;Ivan Titov

  • Affiliations:
  • Univ Geneva;Univ Geneva;Univ Geneva;Univ Illinois at U-C

  • Venue:
  • CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Motivated by the large number of languages (seven) and the short development time (two months) of the 2009 CoNLL shared task, we exploited latent variables to avoid the costly process of hand-crafted feature engineering, allowing the latent variables to induce features from the data. We took a pre-existing generative latent variable model of joint syntactic-semantic dependency parsing, developed for English, and applied it to six new languages with minimal adjustments. The parser's robustness across languages indicates that this parser has a very general feature set. The parser's high performance indicates that its latent variables succeeded in inducing effective features. This system was ranked third overall with a macro averaged F1 score of 82.14%, only 0.5% worse than the best system.