Action verbs have many meanings, covering actions in different ontological types. Moreover, each language categorizes action in its own way. The range of variations within and across languages is largely unknown, causing trouble for natural language processing tasks and second language acquisition. IMAGACT is a corpus-based ontology of action concepts, derived from English and Italian spontaneous speech resources, which makes use of the universal language of images to identify action types. IMAGACT4ALL is an internet infrastructure for mapping languages onto the ontology. Because the action concepts are represented with videos, extension into new languages is done using competence-based judgments by mother-tongue informants without intense lexicographic work involving under determined semantic description. It has been already proved on Spanish and Chinese and it is now in the process of being extended to Hindi, Bengali, Sanskrit and Portuguese. The paper presents the infrastructure and the methodology for mapping languages onto the ontology focusing on the features that make it a promising infrastructure for processing Indian languages.
Added on March 22, 2016
Contributed by : UNIFI, Florence, J.N.U.,New Delhi and UMFG, Belo H
Product Type : Research Paper
License Type : Freeware
System Requirement :
Author : Moneglia Massimo, Brown Susan, Kar Aniruddha, Kumar Anand, Ojha Atul Kr., Mello Heliana, Niharika, Jha Girish Nath, Ray Bhaskar and Sharma, Annu