tailieunhanh - Báo cáo khoa học: "Phoneme-to-Text Transcription System with an Infinite Vocabulary"

The noisy channel model approach is successfully applied to various natural language processing tasks. Currently the main research focus of this approach is adaptation methods, how to capture characteristics of words and expressions in a target domain given example sentences in that domain. As a solution we describe a method enlarging the vocabulary of a language model to an almost infinite size and capturing their context information. | Phoneme-to-Text Transcription System with an Infinite Vocabulary Shinsuke Mori Daisuke Takuma Gakuto Kurata IBM Research Tokyo Research Laboratory IBM Japan Ltd. 1623-14 Shimotsuruma Yamato-shi 242-8502 Japan mori@ Abstract The noisy channel model approach is successfully applied to various natural language processing tasks. Currently the main research focus of this approach is adaptation methods how to capture characteristics of words and expressions in a target domain given example sentences in that domain. As a solution we describe a method enlarging the vocabulary of a language model to an almost infinite size and capturing their context information. Especially the new method is suitable for languages in which words are not delimited by whitespace. We applied our method to a phoneme-to-text transcription task in Japanese and reduced about 10 of the errors in the results of an existing method. 1 Introduction The noisy channel model approach is being successfully applied to various natural language processing NLP tasks such as speech recognition Jelinek 1985 spelling correction Kernighan et al. 1990 machine translation Brown et al. 1990 etc. In this approach an NLP system is composed of two modules one is a taskdependent part an acoustic model for speech recognition which describes a relationship between an input signal sequence and a word the other is a language model LM which measures the likelihood of a sequence of words as a sentence in the language. Since the LM is a common part its improvement augments the accuracies of all NLP systems based on a noisy channel model. Recently the main research focus of LM is shifting to the adaptation method how to capture the characteristics of words and expressions in a target domain. The standard adaptation method is to prepare a corpus in the application domain count the frequencies of words and word sequences and manually annotate new words with their input signal sequences to be added to the vocabulary. .