A new tagging method is presented to build a Chinese semantic corpus. The method characterizes the sentence meaning as a linear sequence of dependency relationships which are the semantic or syntactic relationships b...A new tagging method is presented to build a Chinese semantic corpus. The method characterizes the sentence meaning as a linear sequence of dependency relationships which are the semantic or syntactic relationships between words in the sentence. This representation method is used to build a Chinese statistical parser model to understand the sentence meaning. Specific experiments on automatic telephone switchboard conversations show that the proposed parser has a precision of 80%. This work provides a foundation for building a large-scale Chinese semantic corpus and for research on understanding modeling of the Chinese language.展开更多
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 r...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.展开更多
基金Supported by the National High- Technology DevelopmentProgram of China(No. 863 - 3 0 6- 2 D0 3 - 0 1- 2)
文摘A new tagging method is presented to build a Chinese semantic corpus. The method characterizes the sentence meaning as a linear sequence of dependency relationships which are the semantic or syntactic relationships between words in the sentence. This representation method is used to build a Chinese statistical parser model to understand the sentence meaning. Specific experiments on automatic telephone switchboard conversations show that the proposed parser has a precision of 80%. This work provides a foundation for building a large-scale Chinese semantic corpus and for research on understanding modeling of the Chinese language.
基金Supported by the National High-Tech Research and Development (863) Program of China (No. 2004AA114011-2)
文摘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.
