Automatic crosslingual thesaurus generated from the Hong Kong SAR Police Department Web corpus for crime analysis

Abstract

based approach to align English/Chinese Hong Kong Police press release documents from the Web is first presented. We also introduce an algorithmic approach to generate a robust knowledge base based on statistical correlation analysis of the semantics (knowledge) embedded in the bilingual press release corpus. The research output consisted of a thesaurus-like, semantic network knowledge base, which can aid in semanticsbased crosslingual information management and retrieval.

Enriching a thesaurus as a better question-answering tool and information retrieval aid

“…Searching thesauri, also referred to as end-user thesauri, are defined as a category of thesauri enhanced with a large number of entry terms that are synonyms, quasi-synonyms or term variants which assist end-users in finding alternative terms for query expansion [11,21]. Much work has been done on automatic thesaurus construction and automatic query expansion [9,22–24]. Automatically constructed thesauri based on statistical term co-occurrence have been extensively reported in the literature [25].…”

Automated criminal link analysis based on domain knowledge

“…Structured documents such as crime incident records, bank accounts, and financial transaction records usually do not contain explicit information about entity associations. Unstructured documents such as police report narratives may contain various entities and implicit association information that are difficult to extract (Li & Yang, 2005; Wu & Pottenger, 2005). Prior research has proposed some approaches to help address this problem.…”