Thumbnail
Access Restriction
Open

Author Wang, Ye-Yi ♦ Mahajan, Milind ♦ Huang, Xuedong
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Domain-specific Data Becomes ♦ Spoken Language Processing ♦ Unified Model ♦ Unified Context-free Grammar ♦ Full Potential ♦ Spoken Language Understanding ♦ Domain-independent N-gram Model ♦ Important Formalism ♦ Major Problem ♦ Natural Language ♦ Domainspecific Cfgs ♦ N-gram Model ♦ Speech Recognition ♦ Domainindependent Word Trigram ♦ Context-free Grammar ♦ Word Ngram Model ♦ Excellent Portability ♦ Unified Model Converges ♦ Limited Amount ♦ Domain-independent Application ♦ Unified Recognition ♦ Domain-specific Data
Description While context-free grammars (CFGs) remain as one of the most important formalisms for interpreting natural language, word ngram models are surprisingly powerful for domain-independent applications. We propose to unify these two formalisms for both speech recognition and spoken language understanding (SLU). With portability as the major problem, we incorporated domainspecific CFGs into a domain-independent n-gram model that can improve generalizability of the CFG and specificity of the n-gram. In our experiments, the unified model can significantly reduce the test set perplexity from 378 to 90 in comparison with a domainindependent word trigram. The unified model converges well when the domain-specific data becomes available. The perplexity can be further reduced from 90 to 65 with a limited amount of domain-specific data. While we have demonstrated excellent portability, the full potential of our approach lies in its unified recognition and understanding that we are investigating. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2000-01-01
Publisher Institution in International Conference of Acoustics, Speech, and Signal Processing