The proceedings of the workshop can be accessed here.

Shallow parsing is important for many NLP applications, particularly for information extraction, information retrieval, cross linguistic information access, question answering, etc. Shallow parsing consists of part of speech tagging and chunking. For these analyses both rule based and machine learning approaches are used. A judicious combination of the two give the best results.

Shallow parsing has been developed for English and other European languages. However, not much work has been done in South Asian languages in this direction. These languages have unique characteristics such as relatively free word order, rich case-endings, agglutinative, non-agglutinative etc. which pose challenging problems for shallow parsing. The techniques which work well for English and similar languages do not always yield good results for these languages.

The aim of the workshop is to bring together researchers for a discussion on issues pertaining to shallow parsing in South Asian languages. The workshop will be organised against a shared task contest.