Search

In Example Based Machine Translation (EBMT) research, there are three main approaches: Surface Based, Pattern Based and Structure Based approach. In Structure Based EBMT system, such as SSTC approach [1], it has a problem that it relies on two syntax parsers to analyze the translation examples, but robust syntax parsers are not always available. On the other hand, Chinese and Portuguese belong to two different language families and there exist grammatical deviation problem between them. In order to resolve the weakness of the Structure Based EBMT system and linguistic problems between Chinese and Portuguese, Tang and Wong [2] propose a new Portuguese to Chinese Machine Translation method and this method is based on a novel technology called Translation Corresponding Tree (TCT) which is an example based knowledge annotation method for Portuguese to Chinese translation. In this paper, it adopts the TCT annotation scheme and introduces the knowledge based construction and translation for Chinese to Portuguese MT. In this parper, it presents the additional problems during Chinese analysis and the corresponding solutions. In this research, it also proposes a conversion algorithm to reuse the existing translation knowledge of Portuguese to Chinese MT system, which represented in terms of TCT trees. Based on the transformation algorithm, the knowledge trees of Portuguese to Chinese translation is converted into that of the translation knowledge which can be used to facilitate the Chinese to Portuguese. By this conversion method, existing knowledge can be easily reused without having to re-construct the knowledge from scratch. Based on the research result of this paper, a Chinese to Portuguese prototyping machine translation system is implemented and the empirical results show that the MT system can achieve the translation accuracy of 85% in the domain of Macau Law statements. [ABSTRACT FROM AUTHOR]

Chinese is a challenging language in natural language processing. Unlike other languages like English, Portuguese, the first step in Chinese text processing is the segmentation because there are no delimiters in a Chinese sentence for identifying the words boundaries in it. And there are many ambiguity problems during Chinese processing like segmentation ambiguities, unknown words problem, part-of-speech ambiguities, etc. In segmentation and tagging, one of the main tasks is to identify unknown words and recognize proper nouns. In the research, efforts are being paid on this particular problem. In this paper, an integrated application with segmentation and tagging ability has been studied and implemented. In the segmentation, a line of Chinese text is first split up into a sequence of atomic characters. Like this Chinese statement, (we go to play ball) is split up into with spaces and then for every atomic character in this statement, we are going to search through a knowledge base (necessary statistics about a segmented and tagged Chinese corpus, PFR corpus provided at http://www.icl.pku.edu.cn) to find all the words beginning with those atomic characters and keep this data in an appropriate structure. After that, a depth first search is performed on the data got to generate all the possible segmentations for the Chinese statement based on the words bi-gram model. Upon getting the results, all the candidates are evaluated and the N-best candidate segmentations are selected. In the second phase, an interpolated probabilistic tagging model proposed in [2] with proper nouns recognition and tagging is applied for tagging the N-best candidate segmented Chinese statements. Experiments based on different parameters (e.g., the parameter N used for getting N-best candidate segmentations) were taken for comparison so as to improve the performance of the application. This application is the first step for Chinese processing and it is used as a preprocessing module in the Chinese to Portuguesemachine translation system. [ABSTRACT FROM AUTHOR]