Two Language Models Using Chinese Semantic
Parsing
LI Mingqin;WANG Xia;WANG Zuoying
【期刊名称】《清华大学学报（英文版）》 【年(卷),期】2006(011)005
【摘要】This paper presents two language models that utilize a Chinese semantic dependency parsing technique for speech recognition. The models are based on a representation of the Chinese semantic structure with dependency relations. A semantic dependency parser was described to automatically tag the semantic class for each word with 90.9% accuracy and parse the sentence semantic dependency structure with 75.8% accuracy. The Chinese semantic parsing technique was applied to structure language models to develop two language models, the semantic dependency model (SDM) and the headword trigram model (HTM). These language models were evaluated using Chinese speech recognition. The experiments show that both models outperform the word trigram model in terms of the Chinese character recognition error rate. 【总页数】7页(582-588) 【关键词】language grammar;speech recognition
【作者】LI Mingqin;WANG Xia;WANG Zuoying
model;semantic
parsing;dependency
Two Language Models Using Chinese Semantic Parsing
