Text Retrieval Using SMS Queries: Datasets and Overview of FIRE 2011 Track on SMS-Based FAQ Retrieval

Analytics for noisy text has recently been of much interest. Short text snippets sent using the short messaging service (SMS) has been one of the popular sources of noisy text. Due to a multitude of factors such as inconvenience in using the small mobile keyboard and the inherent carelessness while typing on-the-go, SMS authors often tend to shorten messages using compression techniques such as dropping vowels in words, replacing words by their shorter phonetic substitutions and dropping entire words. Due to the non-standard nature of such shortening, it becomes awkward to process SMSes electronically.

[1]  L. Venkata Subramaniam,et al.  Unsupervised cleansing of noisy text , 2010, COLING.

[2]  Rohiza Ahmad,et al.  SMS-based final exam retrieval system on mobile phones , 2010, 2010 International Symposium on Information Technology.

[3]  L. Venkata Subramaniam,et al.  SMS based Interface for FAQ Retrieval , 2009, ACL.

[4]  Animesh Mukherjee,et al.  Investigation and modeling of the structure of texting language , 2007, International Journal of Document Analysis and Recognition (IJDAR).

[5]  Rahul Goutam,et al.  Experiments with artificially generated noise for cleansing noisy text , 2011, MOCR_AND '11.

[6]  Janet L. Kolodner,et al.  An introduction to case-based reasoning , 1992, Artificial Intelligence Review.