Department of Humanities and Social Sciences
WordNet in the Context on Localization
Dr. S. Arulmozi
November 2, 2017 (Thursday) at 2:00 PM
Venue: Lecture Hall 2
WordNets are vital resource for Natural Language Processing applications and Machine Translation. WordNet was originally conceived and developed lexical database for English on the basis of psycholinguistic properties. The major lexical categories like Nouns, verbs, adjective and adverbs are organized in terms of sets of synonyms (synsets), each representing a lexical concept (Fellbaum, 1998). Synsets are sets of synonyms. They are linked by semantic relations like hypernymy (is-a), meronymy (part-of), troponymy (manner-of) etc. The first WordNet in the world was built for English at Princeton University. The success of the English WordNet has paved way for the emergence of several projects with the aim of constructing WordNets in various languages and developing multilingual WordNets. EuroWordNet, a conglomeration of WordNets in European languages is an important project with a multilingual WordNet. Similarly, in Indian languages, starting from the year 2000, WordNets have been built under the pioneering effort from Hindi WordNet at IIT, Bombay. In this talk, a brief introduction to Princeton English WordNet will be dealt. The talk would also delve on the construction of Indian language WordNets.
Brief Bio-sketch of the speaker
Dr. S. Arulmozi is working as Assistant Professor at the Centre for Applied Linguistics & Translation, University of Hyderabad. He has been engaged in research and teaching in Computational Linguistics, Corpus Studies and WordNet. He received his Ph.D in Applied Linguistics from the University of Hyderabad in 1999. He has written widely over the past two decades and carried out key research projects. He was also influential in coordinating `Common Man’s Multilingual Dictionary (6 volumes)’in 2008