In this paper, we present a two-phase biomedical NE-recognition method based on a ME model: we first recognize biomedical terms and then assign appropriate semantic classes to the recognized terms. In the two-phase NE-recognition method, the performance of the term-recognition phase is very important, because the semantic classification is performed on the region identified at the recognition phase. In this study, in order to improve the performance of term recognition, we try to incorporate lexical knowledge into pre- and postprocessing of the term-recognition phase. In the preprocessing step, we use domain-salient words as lexical knowledge obtained by corpus comparison. In the postprocessing step, we utilize χ 2 -based collocations gained from Medline corpus. In addition, we use morphological patterns extracted from the training data as features for learning the ME-based classifiers. Experimental results show that the performance of NE-recognition can be improved by utilizing such lexical knowledge.

In this paper, we propose a new contextdependent SMT model that is tightly coupled with a language model.It is designed to decrease the translation ambiguities and efficiently search for an optimal hypothesis by reducing the hypothesis search space.It works through reciprocal incorporation between source and target context: a source word is determined by the context of previous and corresponding target words and the next target word is predicted by the pair consisting of the previous target word and its corresponding source word.In order to alleviate the data sparseness in chunk-based translation, we take a stepwise back-off translation strategy.Moreover, in order to obtain more semantically plausible translation results, we use bilingual verb-noun collocations; these are automatically extracted by using chunk alignment and a monolingual dependency parser.As a case study, we experimented on the language pair of Japanese and Korean.As a result, we could not only reduce the search space but also improve the performance.