Learning to Sportscast: A Test of Grounded Language Acquisition
Abstract
We present a novel commentator system that learns language from sportscasts of simulated soccer games. The system learns to parse and generate commentaries without any engineered knowledge about the English language. Training is done using only ambiguous supervision in the form of textual human commentaries and simulation states of the soccer games. The system simultaneously tries to establish correspondences between the commentaries and the simulation states as well as build a translation model. We also present a novel algorithm, Iterative Generation Strategy Learning (IGSL), for deciding which events to comment on. Human evaluations of the generated commentaries indicate they are of reasonable quality compared to human commentaries.
Cite
Text
Chen and Mooney. "Learning to Sportscast: A Test of Grounded Language Acquisition." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390173Markdown
[Chen and Mooney. "Learning to Sportscast: A Test of Grounded Language Acquisition." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/chen2008icml-learning/) doi:10.1145/1390156.1390173BibTeX
@inproceedings{chen2008icml-learning,
title = {{Learning to Sportscast: A Test of Grounded Language Acquisition}},
author = {Chen, David L. and Mooney, Raymond J.},
booktitle = {International Conference on Machine Learning},
year = {2008},
pages = {128-135},
doi = {10.1145/1390156.1390173},
url = {https://mlanthology.org/icml/2008/chen2008icml-learning/}
}