Abstract | ||
---|---|---|
We describe a probabilistic reference disambiguation mechanism developed for a spoken dialogue system mounted on an autonomous robotic agent. Our mechanism receives as input referring expressions containing intrinsic features of individual concepts (lexical item, size and colour) and features involving more than one concept (ownership and location). It then performs probabilistic comparisons between the given features and features of objects in the domain, yielding a ranked list of candidate referents. Our evaluation shows high reference resolution accuracy across a range of spoken referring expressions. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-89197-0_69 | pacific rim international conference on artificial intelligence |
Keywords | Field | DocType |
individual concept,candidate referents,lexical item,Understanding Composite Spoken Descriptions,probabilistic reference disambiguation mechanism,high reference resolution accuracy,intrinsic feature,dialogue system,autonomous robotic agent,probabilistic comparison,Probabilistic Model | Parse tree,Expression (mathematics),Ranking,Computer science,Lexical item,Speech recognition,Natural language processing,Artificial intelligence,Statistical model,Probabilistic logic | Conference |
Volume | ISSN | Citations |
5351 | 0302-9743 | 4 |
PageRank | References | Authors |
0.49 | 7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Enes Makalic | 1 | 55 | 11.54 |
Ingrid Zukerman | 2 | 994 | 113.39 |
Michael Niemann | 3 | 22 | 3.22 |
Daniel F. Schmidt | 4 | 51 | 10.68 |