Word Sense Disambiguation using Static and Dynamic Sense Vectors

Word Sense Disambiguation using Static and Dynamic Sense Vectors Jong-Hoon Oh, and Key-Sun Choi Computer Science Division, Dept. of EECS, Korea Advanced Institute of Science & Technology (KAIST) / Korea Terminology Research Center for Language and Knowledge Engineering (KORTERM), 373-1, Guseong-dong, Yuseong-gu, Daejeon, 305-701, Korea Email: {rovellia,kschoi}@world.kaist.ac.kr Abstract It is popular in WSD to use contextual information in training sense tagged data. Co-occurring words within a limited window-sized context support one sense among the semantically ambiguous ones of the word. This paper reports on word sense disambiguation of English words using static and dynamic sense vectors. First, context vectors are constructed using contextual words 1 in the training sense tagged data. Then, the words in the context vector are weighted with local density. Using the whole training sense tagged data, each sense of a target word2 is represented as a static sense vector in word space, which is the centroid of the context vectors. Then contextual noise is removed using a automatic selective sampling. A automatic selective sampling method use information retrieval technique, so as to enhance the discriminative power. In each test case, a automatic selective sampling method retrieves N relevant training samples to reduce noise. Using them, we construct another sense vectors for each sense of the target word. They are called dynamic sense vectors because they are changed according to a target word and its context. Finally, a word sense of a target word is determined using static and dynamic sense vectors. The English SENSEVAL test suit is used for this experimentation and our method produces relatively good results. 1 ‘Contextual words’ is defined as a list of content words in context. 2 In this paper, a target word ‘Wt’ is a semantically 1. Introduction It is popular in WSD to use contextual information in training data (Agirre, et al., 19963; Escudero, et al., 2000; Gruber, 1991; Schutze, 1998). Co-occurring words within a limited window-sized context support one sense among the semantically ambiguous ones of the word. The problem is to find the most effective patterns in order to capture the right sense. It is true that they have similar context and co-occurrence information when words are used with the same sense (Rigau, et al., 1997). It is also true that contextual words nearby an ambiguous word give more effective patterns or features than those far from it (Chen, et al., 1998). In this paper, we represent each sense of a word as a vector in word space. First, contextual words in the training sense tagged data4 are represented as context vectors. Then, ambiguous word in a given context of ‘Wt’. This context may consist of several sentences and it is represented by ‘contextual words’. 3 Agirre et al., (1996) defines a term ‘conceptual density’ based on how many nodes are hit between WordNet node and target words+contexts. Unlike ‘Conceptual density’, ‘local density’ used in this paper does not use any semantic net like WordNet but use only the contextual words surrounding the given target word.. 4 …

Content truncated to 500 words