An integrated system for building enterprise taxonomies

Abstract

Although considerable research has been conducted in the field of hierarchical text categorization, little has been done on automatically collecting labeled corpus for building hierarchical taxonomies. In this paper, we propose an automatic method of collecting training samples to build hierarchical taxonomies. In our method, the category node is initially defined by some keywords, the web search engine is then used to construct a small set of labeled documents, and a topic tracking algorithm with keyword-based content normalization is applied to enlarge the training corpus on the basis of the seed documents. We also design a method to check the consistency of the collected corpus. The above steps produce a flat category structure 1 which contains all the categories for building the hierarchical taxonomy.Next, linear discriminant projection approach is utilized to construct more meaningful intermediate levels of hierarchies in the generated flat set of categories. Experimental results show that the training corpus is good enough for statistical classification methods.

Topic taxonomy adaptation for group profiling

“…However, human beings are sometimes involved to aid the construction of taxonomies [Zhang et al 2004;Gates et al 2005], making it rather complicated to evaluate. Here, we concentrate on those methods constructing taxonomies automatically.…”

Taxonomies by the numbers

“…Most current approaches for creating taxonomies and the corresponding automated classifiers try to minimize the number of labeled training documents needed by various technologies that either use some sort of bootstrapping or clustering based on a set of documents [1,5,7] or seeding the process based on some examples that are (semi-)automatically extended [12,19]. Our approach focuses on using document sets retrieved based on search engine queries defined per category.…”