Seeking Acronym Definitions: a Web-based Approach

Acronyms are widely used in many domains to abbreviate and stress important concepts. Due to its dynamicity and unbounded nature, manual attempts to compose a global scale repository of acronym-definition pairs result in an overwhelming amount of work and limited amount of results. Attending these shortcomings, the paper presents an automatic and non-supervised methodology to generate acronyms and extract their possible definitions from the Web. The method has been designed in order to minimize the set of constraints, offering a domain and -partially- language independent solution. The obtained results have been manually evaluated against the largest manually built acronym repository (Acronym Finder). The results obtained after this comparison show that the proposed automatic web-based approach is able to improve the coverage of manual attempts offering a high precision. Keywords. Acronyms, information extraction, Web mining.

• Type: Conference
• Year: 2009
• Where: CCIA
• Authors: David Sánchez, David Isern
• Keywords: Acronyms, Artificial Intelligence, CCIA 2009, Global Scale Repository, Manual Attempts