The paper presents an on-going work on accessing unstructured data in the web through mobile devices. To achieve this we use Information Extraction (IE) to extract relevant information from unstructured documents. Here the relevant information are extracted are stored into a database, where a user can search information by giving a query through mobile. The extracted information that matches with the given query in the database are retrieved and presented in a mobile environment. The information extracted is used for searching through the mobile device. This work is done for two languages, English and Tamil. The search facility is provided for text documents that exists in the mobile as well as on the web and the results are presented in the mobile.

1. Alpa Jain, Panagiotis G. Ipeirotis, AnHai Doan, Luis Gravano, Join Optimization of Information Extraction Output. Columbia University, New York University, University of Wisconsin-Madison.
2. Anand Kumar M, Dhanalakshmi V, Soman K. P,2010. A Sequence Labeling Approach to Morphological Analyzer for Tamil Language. Computational Engineering and Networking (CEN), AMRITA Vishwa Vidyapeetham,Coimbatore, India.
3. Dhanalakshmi V, Anand Kumar M, Soman K. P, CEN, Amrita Vishwa, 2010. Natural Language Processing Tools for Tamil Grammar Learning and Teaching. Vidyapeetham Coimbatore, India.
4. Fabio Ciravegna. Adaptive Information Extraction from Text
5. by Rule Induction and Generalisation. Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, S1 4DP Sheffield, UK
6. S. Lakshmana Pandian, T. V. Geetha, 2009. Semantic Role Labeling for Tamil Documents. Department of Computer Science and Engineering, ANNAUNIVERSITY, Chennai, India.
7. Raymond J. Mooney and Un Yong Nahm. Text Mining with Information Extraction. Raymond J. Mooney and Un Yong Nahm
8. Department of Computer Sciences, University of Texas, Austin, TX 78712-1188.

Morphological Analyzer Tokenizer Parts Of Speech Tagger And Chunker Named Entity Recognizer