Paper: Fast Online Lexicon Learning for Grounded Language Acquisition

ACL ID P12-1045
Title Fast Online Lexicon Learning for Grounded Language Acquisition
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

Learning a semantic lexicon is often an impor- tant first step in building a system that learns to interpret the meaning of natural language. It is especially important in language ground- ing where the training data usually consist of language paired with an ambiguous perceptual context. Recent work by Chen and Mooney (2011) introduced a lexicon learning method that deals with ambiguous relational data by taking intersections of graphs. While the al- gorithm produced good lexicons for the task of learning to interpret navigation instructions, it only works in batch settings and does not scale well to large datasets. In this paper we intro- duce a new online algorithm that is an order of magnitude faster and surpasses the state- of-the-art results. We show that by changing the grammar of t...