Abstract
Current systems that learn to process natural language require laboriously constructed human-annotated training data. Ideally, a computer would be able to acquire language like a child by being exposed to linguistic input in the context of a relevant but ambiguous perceptual environment. As a step in this direction, we present a system that learns to sportscast simulated robot soccer games by example. The training data consists of textual human commentaries on Robocup simulation games. A set of possible alternative meanings for each comment is automatically constructed from game event traces. Our previously developed systems for learning to parse and generate natural language (KRISP and WASP) were augmented to learn from this data and then commentate novel games. The system is evaluated based on its ability to parse sentences into correct meanings and generate accurate descriptions of game events. Human evaluation was also conducted on the overall quality of the generated sportscasts and compared to human-generated commentaries.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mooney, R.J. (2008). Learning Language from Its Perceptual Context. In: Daelemans, W., Goethals, B., Morik, K. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2008. Lecture Notes in Computer Science(), vol 5211. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87479-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-87479-9_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87478-2
Online ISBN: 978-3-540-87479-9
eBook Packages: Computer ScienceComputer Science (R0)