Abstract | ||
---|---|---|
This paper focuses on the learning of multi-word lexical units, or phrases, and how to model them within the vari- able n-gram framework. We introduce the notion of context- dependent phrases and suggest an algorithm for unsuper- vised learning of phrases. Also, we propose an approach to integrate a phrase grammar and a variable n-gram with- out the need of explicitly handling multi-word lexical items. The combined variable n-gram phrase grammar improves recognition accuracy on the Switchboard corpus over both the baseline trigram and using a variable n-gram alone. |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/ICASSP.2000.862063 | ICASSP |
Keywords | Field | DocType |
natural languages,speech,information systems,unsupervised learning,speech recognition,nomograms,linguistics,maximum likelihood estimation,context dependent | Head-driven phrase structure grammar,Computer science,Phrase,Dependency grammar,Lexical functional grammar,Phrase structure rules,Artificial intelligence,Natural language processing,Noun phrase,Pattern recognition,Subcategorization,ID/LP grammar,Speech recognition | Conference |
Volume | ISSN | ISBN |
3 | 1520-6149 | 0-7803-6293-4 |
Citations | PageRank | References |
2 | 0.67 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manhung Siu | 1 | 464 | 61.40 |
Mari Ostendorf | 2 | 2462 | 348.75 |