ISSN: 2182-2069 (printed) / ISSN: 2182-2077 (online)
Improving Terminologies Synonym Expansion Model for Cultural Heritage Contents
The huge volume of cultural heritage domain requires the users to be more specific in their needs. The vocabulary problem and access points. These are the challenging issues facing the cultural heritage information retrieval researchers. Therefore, there is a rising need for models that would handle these problem and professional search systems that would allow users to search effectively in a cultural heritage domain. For cultural heritage content, normally the users also include a large group of non-experts. As such, there is a need for better access models to this rich contents. In this research, a model is proposed for cultural heritage content called terminologies synonym expansion (TSE) model. This proposed model combines the power of the TextRank algorithm for terminology identification, the comprehensive WordNet lexical database for synonym expansion, and the linking of synonyms to their respective terminologies. Together, these steps aim to bridge the vocabulary gap between non-expert users and the specialized terms used within the cultural heritage domain. The experiments on cultural heritage collections CHiC2013 and CHiC2013_EDE show a significant improvement over conventional retrieval of information on cultural heritage collections.