The Sinica Sense Management System: Design and Implementation

Abstract

A sense-based lexical knowledgebase is a core foundation for language engineering. Two important criteria must be satisfied when constructing a knowledgebase: linguistic felicity and data cohesion. In this paper, we discuss how data cohesion of the sense information collected using the Sinica Sense Management System (SSMS) can be achieved. SSMS manages both lexical entries and word senses, and has been designed and implemented by the Chinese Wordnet Team at Academia Sinica. SSMS contains all the basic information that can be merged with the future Chinese Wordnet. In addition to senses and meaning facets, SSMS also includes the following information: POS, example sentences, corresponding English synset(s) from Princeton WordNet, and lexical semantic relations, such as synonym/antonym and hypernym/hyponym. Moreover, the overarching structure of the system is managed by using a sense serial number, and an inter-entry structure is established by means of cross-references among synsets and homographs. SSMS is not only a versatile development tool and management system for a sense-based lexical knowledgebase. It can also serve as the database backend for both Chinese Wordnet and any sense-based applications for Chinese language processing.