Abstract | ||
---|---|---|
Many people are now routinely building grammar-based language models for interactive spoken language applications; these language models are typically ad hoc semantic grammars which ignore many standard linguistic constraints, in particular grammatical agreement. We describe a series of experiments in which we took three CFG-based language models from non-trivial implemented systems, and in each case contrasted the performance of a version which included agreement constraints against a version which ignored them. Our findings suggest that inclusion of agreement constraints significantly improves performance in terms of both word error rate and semantic error rate. |
Year | DOI | Venue |
---|---|---|
2001 | 10.3115/1073336.1073366 | NAACL |
Keywords | Field | DocType |
grammar-based language model,agreement constraint,language model,standard linguistic constraint,word error rate,semantic error rate,language application,cfg-based language model,particular grammatical agreement,error rate,speech recognition,context free grammars | Rule-based machine translation,Logic error,Cache language model,Context-free grammar,Computer science,Grammar,Natural language processing,Artificial intelligence,Universal Networking Language,Language model,Spoken language | Conference |
Citations | PageRank | References |
5 | 1.04 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manny Rayner | 1 | 508 | 89.27 |
Genevieve Gorrell | 2 | 266 | 22.00 |
Beth Ann Hockey | 3 | 212 | 36.35 |
John Dowding | 4 | 71 | 17.10 |
Johan Boye | 5 | 221 | 20.69 |