Terminology Extraction for and from Communications in Multi-disciplinary Domains

Terminology extraction generally refers to methods and systems for identifying term candidates in a uni-disciplinary and uni-lingual environment such as engineering, medical, physical and geological sciences, or administration, business and leisure. However, as human enterprises get more and more complex, it has become increasingly important for teams in one discipline to collaborate with others from not only a non-cognate discipline but also speaking a different language. Disaster mitigation and recovery, and conflict resolution are amongst the areas where there is a requirement to use standardised multilingual terminology for communication. This paper presents a feasibility study conducted to build terminology (and ontology) in the domain of disaster management and is part of the broader work conducted for the EU project Sland ´ ail (FP7 607691). We have evaluated CiCui (for Chinese name ´ 词萃, which translates to words gathered), a corpus-based text analytic system that combine frequency, collocation and linguistic analyses to extract candidates terminologies from corpora comprised of domain texts from diverse sources. CiCui was assessed against four terminology extraction systems and the initial results show that it has an above average precision in extracting terms.