Author:
Li Juanzi, Huang Changning

Abstract:
Word sense disambiguation is one of the most difficult problems in natural language processing. This paper puts forward a model of mapping a structural semantic space from a thesaurus into a multi-dimensional, real-valued vector space and gives a word sense disambiguation method based on this mapping. The model, which uses an unsupervised learning method for acquiring the disambiguation knowledge, not only saves extensive manual work, but also realizes the sense tagging of a large amount of content words. Firstly, a Chinese thesaurus Cilin and a very large-scale corpus are used to construct the structure of the semantic space. Then, a dynamic disambiguation model is developed to disambiguate an ambiguous word according to the vectors of monosemous words in each of its possible categories. In order to resolve the problem of data sparseness, a method is proposed to make the model more robust. Testing results show that the model has a relatively good performance and can also be used for other languages.

Keyword:
Natural language processing, Word sense disambiguation, Unsupervised learning, Vector space, Language modeling

Author:
Hsin-Hsi Chen, Guo-Wei Bian and Wen-Cheng Lin

Abstract:
This paper deals with translation ambiguity and target polysemy problems together. Two monolingual balanced corpora are employed to learn word co-occurrence for the purpose of translation ambiguity resolution and augmented translation restrictions for that of target polysemy resolution. Experiments show that the model achieves 62.92% monolingual information retrieval, which is 40.80% better than that of the select-all model. When target polysemy resolution is added, the retrieval performance represents approximately a 10.11% increase over that of the model which resolves translation ambiguity only.

Keyword:
Cross-language information retrieval, Query translation, Translation ambiguity, Target polysemy, Augmented translation restriction