Use and acquisition of semantic language model

Authors:
Kuansan Wang;Ye-Yi Wang;Alex Acero
Affiliations:
Microsoft Research, One Microsoft Way, Redmond, WA;Microsoft Research, One Microsoft Way, Redmond, WA;Microsoft Research, One Microsoft Way, Redmond, WA
Venue:
HLT-NAACL--Demonstrations '04 Demonstration Papers at HLT-NAACL 2004
Year:
2004

Citing 1
Cited 1

Hidden understanding models of natural language

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics

Using domain knowledge about medications to correct recognition errors in medical report creation

Louhi '10 Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents

Quantified Score

Hi-index	0.00

Visualization

Abstract

Semantic language model is a technique that utilizes the semantic structure of an utterance to better rank the likelihood of words composing the sentence. When used in a conversational system, one can dynamically integrate the dialog state and domain semantics into the semantic language model to better guide the speech recognizer executing the decoding process. We describe one such application that employs semantic language model to cope with spontaneous speech in a robust manner. The semantic language model, though can be manually crafted without data, can benefit significantly from data driven machine learning techniques. An example based approach is also described here to demonstrate a viable approach.