Towards a Semantic Annotation of English Television News - Building and Evaluating a Constraint Grammar FrameNet

Copyright 2012 by Shaohua Yang, Hai Zhao, and Bao-liang Lu 26th Pacific Asia Conference on Language,Information and Computation pages 333–342 A Machine Translation Approach for Chinese Whole-Sentence Pinyin-to-Character Conversion∗ Shaohua Yang and Hai Zhao† and Bao-liang Lu MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering, Shanghai Jiao Tong University 800 Dongchuan Road, Shanghai 200240, China shyang.ok@gmail.com, zhaohai@cs.sjtu.edu.cn, blu@cs.sjtu.edu.cn Abstract This paper introduces a new approach to solve the Chinese Pinyin-to-character (PTC) con- version problem. The conversion from Chi- nese Pinyin to Chinese character can be re- garded as a transformation between two dif- ferent languages (from the Latin writing sys- tem of Chinese Pinyin to the character form of Chinese,Hanzi), which can be naturally solved by machine translation framework. PTC prob- lem is usually regarded as a sequence label- ing problem, however, it is more difficult than any other general sequence labeling problems, since it requires a large label set of all Chinese characters for the labeling task. The essential difficulty of the task lies in the high degree of ambiguities of Chinese characters correspond- ing to Pinyins. Our approach is novel in that it effectively combines the features of continu- ous source sequence and target sequence. The experimental results show that the proposed approach is much faster, besides, we got a better result and outperformed the existing se- quence labeling approaches. 1 Introduction There are more than twenty thousand different Chi- nese characters adopted by Chinese language so that ∗This work was partially supported by the National Natu- ral Science Foundation of China (Grant No. 60903119 and Grant No. 61170114), the National Research Foundation for the Doctoral Program of Higher Education of China under Grant No. 20110073120022, the National Basic Research Program of China (Grant No. 2009CB320901) and the European Union Seventh Framework Programme (Grant No. 247619). †Corresponding author it is a difficult task to type the Chinese character di- rectly from a Latin-style keyboard. Chinese Pinyin is such an encoding scheme that can map the Chi- nese character to a group of Latin letters so that each character usually has an unique Pinyin rep- resentation1. Pinyin is originally designed as the phonetic symbol of a Chinese character. For exam- ple, Pinyin for the Chinese character “我 我 我”(I,me) is “wo”. As one of the most important topic in Chinese natural language process, Pinyin-to-character(PTC) problem refers to the automatic transformation from Chinese Pinyin sequence to Chinese character se- quence. It plays an important or even key role in areas such as speech recognition, Chinese keyboard input method and etc. There are five different tones for Chinese pronun- ciation. In Chinese Pinyin system, tone is repre- sented as an accent symbol over Latin letters, which is not convenient to input and thus usually ignored in most Chinese keyboard input methods. The Chinese PTC problem can be very challeng- ing for the following reasons: there are about 410 Pinyins(without considering five different tones), however, there are ten …

Content truncated to 500 words