Learning Dependency-Based Compositional Semantics
Percy Liang, Michael I. Jordan, Dan Klein · Computational Linguistics · 2012
Suppose we want to build a system that answers a natural language question by representing its semantics as a logical forxm and computing the answer given a structured database of facts. The core part of such a system is the semantic parser that maps questions to logical forms. Semantic parsers are typically trained from examples of questions annotated with their target logical forms, but this type of annotation is expensive. Our goal is to instead learn a semantic parser from question–answer pairs, where the logical form is modeled as a latent variable. We develop a new semantic formalism, dependency-based compositional semantics (DCS) and define a log-linear distribution over DCS logical forms. The model parameters are estimated using a simple procedure that alternates between beam search and numerical optimization. On two standard semantic parsing benchmarks, we show that our system obtains comparable accuracies to even state-of-the-art systems that do require annotated logical forms.
Cited by 546 works. doi:10.1162/coli_a_00127 Open-access PDF
Authors
References
- A Stochastic Approximation Method
- Building a Large Annotated Corpus of English: The Penn Treebank
- An algorithm for suffix stripping
- Abstract interpretation
- Head-Driven Statistical Models for Natural Language Parsing
- Updating Quasi-Newton Matrices with Limited Storage
- Graphical Models, Exponential Families, and Variational Inference
- The Proper Treatment of Quantification in Ordinary English
- Learning accurate, compact, and interpretable tree annotation
- The Syntactic Process