Category-associated collocative concept primitives extraction

Abstract

Collocation is studied as an essential linguistic phenomenon in traditional natural language processing. Similarity, collocative concept primitives are introduced in HNC Concept Primitive Space to present the concept primitive pair co-occurring frequently. Collocative concept primitives can be studied with categories together as concept primitives usually contain category information. To explore the collocation phenomenon in the field of HNC and apply collocative information to language processing, this paper presents a two-stage approach to extract category-associated collocative concept primitives from a classification corpus. By conducting collocative concept primitives extraction in each sub-category corpus and carrying out category-associated collocative concept primitives extraction in the summarized corpus, we generate a category-associated collocative concept primitives list for each category. Our experiments show the items we extract are consistent with the reality and are of significance.