Work

Learning context-dependent mappings from sentences to logical form

Year: 2009

Type: conference-paper

Abstract: We consider the problem of learning context-dependent mappings from sentences to logical form. The training examples are sequences of sentences annotated with lambda-calculus meaning representations. We develop an algorithm that maintains explicit, lambda-calculus representations of salient discourse entities and uses a context-dependent analysis pipeline to recover logical forms. The method uses a hidden-variable variant of the perception algorithm to learn a linear model used to select the best analysis. Experiments on context-dependent utterances from the ATIS corpus show that the method recovers fully correct logical forms with 83.7% accuracy.

DOI: 10.3115/1690219.1690283

Authors: Luke S. Zettlemoyer, Michael Collins

Institution: MIT Computer Science and Artificial Intelligence Laboratory

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W2142898321

FWCI: 11.73

Cites: 25

Cited by: 178

Related to: 10