Automatic Word Sense Discrimination-英文文献.pdf

Automatic Word Sense Discrimination H i n r i c h Sch{itze* Xerox Palo Alto Research Center This paper presents context-group discrimination, a disambiguation algorithm based on cluster- ing. Senses are interpreted as groups (or clusters) of similar contexts of the ambiguous word. Words, contexts, and senses are represented in Word Space, a high-dimensional, real-valued space in which closeness corresponds to semantic similarity. Similarity in Word Space is based on second-order co-occurrence: two tokens (or contexts) of the ambiguous word are assigned to the same sense cluster if the words they co-occur with in turn occur with similar words in a training corpus. The algorithm is automatic and unsupervised in both training and application: senses are inducedfrom a corpus without labeled training instances or other external knowledge sources. The paper demonstrates good performance of context-group discrimination for a sample of natural and artificial ambiguous words. 1. Introduction Word sense disambiguation is the task of assigning sense labels to occurrences of an ambiguous word. This problem can be divided into two subproblems: sense discrimi- nation and sense labeling. Sense discrimination divides the occurrences of a word into a number of classes by determining for any two occurrences whether they belong to the same sense or not. Sense labeling assigns a sense to each class, and, in combination with sense discrimination, to each occurrence of the ambiguous word. This view of disambiguation as a two-stage process may not be completely general (for example, it ma y not be appropriate for the iterative process by which a lexicographer