Abstract
We introduce a new method for automatically disambiguation of word translations by using collocations. In our approach, we learn the the relationships between translation categories and collocations using the information on the Web. The method consists of a training stage and a runtime stage. During the training stage, the method involves automatically acquisition of collocates of target words from a large corpus, distinguishing of collocations into two or more parts by translations of a given word, and learning a translation decision list based on sentences with the target word and its collocates automatically acquired from the Web. At runtime, the target word in the given sentence is translated according to the decision list model. We also describe the implementation of a prototype system of the proposed method, experiments, and evaluation. In the experiment, we used four polysemous words to assess the performance of the method compare the results against judgments made by human subjects. Experimental results indicate that the proposed unsupervised method based on the Web as corpus overcomes the knowledge acquisition bottleneck and provides a promising approach for word translation disambiguation.