Paper: Corpus-based Interpretation of Instructions in Virtual Environments

ACL ID P12-2036
Title Corpus-based Interpretation of Instructions in Virtual Environments
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2012
Authors

Previous approaches to instruction interpre- tation have required either extensive domain adaptation or manually annotated corpora. This paper presents a novel approach to in- struction interpretation that leverages a large amount of unannotated, easy-to-collect data from humans interacting with a virtual world. We compare several algorithms for automat- ically segmenting and discretizing this data into (utterance, reaction) pairs and training a classifier to predict reactions given the next ut- terance. Our empirical analysis shows that the best algorithm achieves 70% accuracy on this task, with no manual annotation required.