Paper: Unsupervised Template Mining for Semantic Category Understanding

ACL ID D14-1087
Title Unsupervised Template Mining for Semantic Category Understanding
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

We propose an unsupervised approach to constructing templates from a large collec- tion of semantic category names, and use the templates as the semantic representa- tion of categories. The main challenge is that many terms have multiple meanings, resulting in a lot of wrong templates. Sta- tistical data and semantic knowledge are extracted from a web corpus to improve template generation. A nonlinear scoring function is proposed and demonstrated to be effective. Experiments show that our approach achieves significantly better re- sults than baseline methods. As an imme- diate application, we apply the extracted templates to the cleaning of a category col- lection and see promising results (preci- sion improved from 81% to 89%).