About the school Research in the area of NLP for Indian languages in the past few years has led to development of various processing techniques and tools which are based on an understanding of the linguistic nature of Indian languages. POS taggers and chunkers have been developed for various Indian languages. These form the base for full sentence parsing. IIIT-H is organising a Workshop on Computational Grammatical Models for Indian Languages from June 9-11. The Workshop is the first step in the direction of exploring the existing linguistic formalisms/frameworks for developing tree banks and parsers for Indian languages. While most of the work reported in literature is based on constituent based grammatical models, there has been an upsurge of literature proposing dependency grammar based models for relatively free word order languages. The workshop will bring together researchers working in the area of linguistics and NLP with invited speakers in the area of generative linguistics, Paninian grammatical framework ( a dependency grammar approach), linguistic typology of Indian languages etc. The focus of discussions will be on the ease of computation and applicability of these models for developing parsers for Indian languages. Another area of discussion will be shallow parsers for Indian languages. The workshop will consist of a set of invited talks and discussions. The first day of the workshop will be a Symposium having presentations of the projects carried out by various groups during the Advanced Summer School organised by IIIT, Hyderabad from May 23 to June 9, 2008. |
