Concept Space Synset Manager Tool

The IndoWordNet 1 Consortium consists of member institutions developing WordNet using the expansion approach. The WordNets developed using expansion approach are very much influenced by the source language and may not reflect the richness of the target language (Walawalikar et al., 2010). And therefore the IndoWordNet Community decided to develop concepts which were specific to their respective language viz. language-specific concepts which will help in increasing the WordNet coverage. Besides the above requirement it was also felt that it should be possible to maintain additional information about the concepts i.e. an image, document describing the concept, links to websites and other resources, etc. In this paper, we discuss a Concept Space Synset Management Tool (CSS) 2 which was developed to assist creation of language specific concepts/synsets and manage their linkages to other Indian language WordNets. 1 Background and Motivation The IndoWordNet is a multilingual WordNet which links WordNets of different Indian languages on a common identification number 1 http://www.cfilt.iitb.ac.in/indowordnet 2 http://indradhanush.unigoa.ac.in/concep tspace called as synset Id given to each concept (Bhattacharyya, 2010). WordNet is designed to capture the vocabulary of a language and can be considered as a dictionary cum thesaurus and much more (Miller, et al., 1993; Miller, 1995; Fellbaum, 1998). Synset (Fellbaum, 1998) is composed of a gloss describing the concept, example sentences and a set of synonym words that are used for the concept. Besides synset data, WordNet maintains many lexical and semantic relations. Table1 gives the number of concepts/synsets created by the language groups of the Indradhanush WordNet Consortium which is a part of the IndoWordNet Consortium. Table1: Synset linkage status Also a sense marked newspaper corpus (sense marking is a task to tag each word of the corpus with the WordNet sense) consisting of minimum 1,00,000 words has been created by each of the members of the Indradhanush WordNet Consortium. The coverage is found to be low. In order to increase the coverage of the WordNet it was decided that a corpus will be created by all language groups and the corpus will be sense marked. To increase the coverage it was decided to add the concepts which were specific to their respective language viz. language-specific concepts and nullify the effect of influence of the source language on the target language WordNet. The CSS Manager Tool 3 was developed to assist in creation of language-specific concepts, linking to other language WordNets, providing additional information about synsets, etc. The features and the detailed framework of the CSS Manager Tool is explained in section 3 and 4. The rest of the paper is organized as follows – section 2 introduces the related work. The features of CSS Manager Tool are presented in section 3; section 4 presents the architecture of CSS Manager Tool. Section 5 presents the implementation details followed by the conclusion and future work.