Confidence Driven Unsupervised Semantic Parsing.

Dan Goldwasser     Roi Reichart     James Clarke     Dan Roth    
Association for Computational Linguistics (ACL), 2011
[pdf]

Abstract

Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data, and introduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. Evaluated over Geoquery, a standard dataset for this task, our system achieved 66% accuracy, compared to 80% of its fully supervised counterpart, demonstrating the promise of unsupervised approaches for this task.


Bib Entry

  @InProceedings{GRCR_acl_2011,
    author = "Dan Goldwasser and Roi Reichart and James Clarke and Dan Roth",
    title = "Confidence Driven Unsupervised Semantic Parsing.",
    booktitle = "Association for Computational Linguistics (ACL)",
    year = "2011"
  }