Unsupervised methods for developing taxonomies by combining syntactic and statistical information

Unsupervised methods for developing taxonomies by combining syntactic and statistical information Dominic Widdows Center for the Study of Language and Information, Stanford University dwiddows@csli.stanford.edu Abstract This paper describes an unsupervised algo- rithm for placing unknown words into a taxon- omy and evaluates its accuracy on a large and varied sample of words. The algorithm works by first using a large corpus to find semantic neighbors of the unknown word, which we ac- complish by combining latent semantic analy- sis with part-of-speech information. We then place the unknown word in the part of the tax- onomy where these neighbors are most concen- trated, using a class-labelling algorithm devel- oped especially for this task. This method is used to reconstruct parts of the existing Word- Net database, obtaining results for common nouns, proper nouns and verbs. We evaluate the contribution made by part-of-speech tag- ging and show that automatic filtering using the class-labelling algorithm gives a fourfold im- provement in accuracy. 1 Introduction The importance of automatic methods for enriching lex- icons, taxonomies and knowledge bases from free text is well-recognized. For rapidly changing domains such as current affairs, static knowledge bases are inadequate for responding to new developments, and the cost of building and maintaining resources by hand is prohibitive. This paper describes experiments which develop auto- matic methods for taking an original taxonomy as a skele- ton and fleshing it out with new terms which are discov- ered in free text. The method is completely automatic and it is completely unsupervised apart from using the origi- nal taxonomic skeleton to suggest possible classifications for new terms. We evaluate how accurately our meth- ods can reconstruct the WordNet taxonomy (Fellbaum, 1998). The problem of enriching the lexical information in a taxonomy can be posed in two complementary ways. Firstly, given a particular taxonomic class (such as fruit) one could seek members of this class (such as apple, ba- nana). This problem is addressed by Riloff and Shepherd (1997), Roark and Charniak (1998) and more recently by Widdows and Dorow (2002). Secondly, given a partic- ular word (such as apple), one could seek suitable tax- onomic classes for describing this object (such as fruit, foodstuff). The work in this paper addresses the second of these questions. The goal of automatically placing new words into a taxonomy has been attempted in various ways for at least ten years (Hearst and Sch¨utze, 1993). The process for placing a word w in a taxonomy T using a corpus C often contains some version of the following stages: • For a word w, find words from the corpus C whose occurrences are similar to those of w. Consider these the ‘corpus-derived neighbors’ N(w) of w. • Assuming that at least some of these neighbors are already in the taxonomy T , map w to the place in the taxonomy where these neighbors are most con- centrated. Hearst and Sch¨utze (1993) added 27 words to Word- Net using a version of this process, with a 63% ac- …

Content truncated to 500 words