Two Language Models Using Chinese Semantic Parsing

• 作 者: 李明琴 王侠 王作英
• 机 构: Department of Electronic Engineering Tsinghua University,Department of Electronic Engineering Tsing
• 出 处: Tsinghua Science and Technology
• 发表日期: 2006年05期
• 关键词: dependency semantic sentence merging syntactic smoothed interpolation sentences

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 struc- ture with dependency relations. A semantic dependency parser was described to automatically tag the se- mantic 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.

This paper presents two language models that utilizes a Chinese semantic dependency parsing technique for speech recognition. The models are based on a representation of the Chinese semantic strucure 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.