One of the key challenges in grounded language acquisition is resolving the intentions of the expressions. Typically the task involves identifying a subset of records from a list of candidates as the correct meaning of a sentence. While most current work assume complete or partial independence be- tween the records, we examine a scenario in which they are strongly related. By representing the set of potential meanings as a graph, we explicitly encode the relationships between the candidate meanings. We introduce a refinement algorithm that first learns a lexicon which is then used to remove parts of the graphs that are irrelevant. Experiments in a navigation domain shows that the algorithm successfully recovered over three quarters of the correct semantic content.

PDF

In Proceedings of Symposium on Machine Learning in Speech and Language Processing (MLSLP 2011), June 2011.

@inproceedings{chen.mlslp11, title={Panning for Gold: Finding Relevant Semantic Content for Grounded Language Learning}, author={David L. Chen and Raymond J. Mooney}, booktitle={Proceedings of Symposium on Machine Learning in Speech and Language Processing (MLSLP 2011)}, month={June}, url="http://www.cs.utexas.edu/users/ai-lab?chen:mlslp11", year={2011} }

Slides (PDF)