Gloss-based word domain assignment

Domain dictionary is very useful in many Natural Language Processing (NLP) applications. This paper proposes a gloss-based word domain assignment algorithm to build domain dictionaries from machine-readable dictionary. Experiments on WordNet2.0 show that 62.53% of the first domain labels can match with the WordNet Domains3.0. Compared with the traditional corpus-based word domain assignment algorithms, this method can effectively use the existing dictionary resource and improve the accuracy of word domain assignment while reducing human efforts on corpus collection.