Abstract | ||
---|---|---|
The most common speech understanding architecture for spoken dialogue systems is a combination of speech recognition based on a class N-gram language model, and robust parsing. For many types of applications, however, grammar-based recognition can offer concrete advantages. Training a good class N-gram language model requires substantial quantities of corpus data, which is generally not available at the start of a new project. Head-to-head comparisons of class N-gram/robust and grammar-based systems also suggest that users who are familiar with system coverage get better results from grammar-based architectures (Knight et al., 2001). As a consequence, deployed spoken dialogue systems for real-world applications frequently use grammar-based methods. This is particularly the case for speech translation systems. Although leading research systems like Verbmobil and NE-SPOLE! (Wahlster, 2000; Lavie et al., 2001) usually employ complex architectures combining statistical and rule-based methods, successful practical examples like Phraselator and S-MINDS (Phraselator, 2005; Sehda, 2005) are typically phrasal translators with grammar-based recognizers. |
Year | DOI | Venue |
---|---|---|
2005 | 10.3115/1225733.1225747 | HLT/EMNLP |
Keywords | Field | DocType |
class n-gram language model,grammar-based recognition,grammar-based method,grammar-based system,good class n-gram language,class n-gram,grammar-based recognizers,grammar specialization,dialogue system,common speech understanding architecture,grammar-based architecture,japanese speech understanding | Computer science,Operator-precedence grammar,Grammar systems theory,Natural language processing,Artificial intelligence,Language model,Architecture,Emergent grammar,Speech recognition,Grammar,Parsing,Speech translation,Machine learning | Conference |
Volume | Citations | PageRank |
H05-2 | 4 | 0.75 |
References | Authors | |
3 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manny Rayner | 1 | 508 | 89.27 |
Nikos Chatzichrisafis | 2 | 35 | 6.17 |
Pierrette Bouillon | 3 | 214 | 41.22 |
Yukie Nakao | 4 | 47 | 8.86 |
Hitoshi Isahara | 5 | 1267 | 165.21 |
Kyoko Kanzaki | 6 | 168 | 22.73 |
Beth Ann Hockey | 7 | 212 | 36.35 |
Marianne Santaholma | 8 | 27 | 6.00 |
Marianne Starlander | 9 | 38 | 9.54 |