Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

TL;DR

This paper introduces a probabilistic categorial grammar-based learning algorithm that maps natural language sentences to lambda-calculus representations, improving semantic parsing for database interfaces.

Contribution

It presents a novel learning approach that induces a grammar and probabilistic model from labeled data, enhancing semantic parsing accuracy.

Findings

Outperforms previous methods on benchmark database domains

Induces a grammar and log-linear model from training data

Effective for natural language interfaces to databases

Abstract

This paper addresses the problem of mapping natural language sentences to lambda-calculus encodings of their meaning. We describe a learning algorithm that takes as input a training set of sentences labeled with expressions in the lambda calculus. The algorithm induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. We apply the method to the task of learning natural language interfaces to databases and show that the learned parsers outperform previous methods in two benchmark database domains.