Data-Driven Methods for SMS-Based FAQ Retrieval

• Published in: Multilingual Information Access in South Asian Languages pp. 104 - 118
• Main Authors: Bhattacharya, Sanmitra, Tran, Hung, Srinivasan, Padmini
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2013
• Series: Lecture Notes in Computer Science
• Subjects: Relevance Judgment; Retrieval Experiment; Retrieval Problem; Retrieval Strategy; Text Messaging
• DOI: 10.1007/978-3-642-40087-2_11
• ISBN: 9783642400865; 3642400868
• ISSN: 0302-9743

SMS text messaging is one of the most popular data applications on mobile phones these days. Other than personal communication, text messaging can also be used for various purposes like bill payment, banking, inquiry, etc. However these messages are extremely noisy and contain misspellings, abbreviations, transliterations, etc. Keeping this in mind, FIRE 2011 introduced a new retrieval task called SMS-based FAQ retrieval in English, Hindi and Malayalam. Within-language and cross-language tasks were designed for this retrieval problem. As solutions we propose various data-driven retrieval techniques that includes noise reduction in the SMS queries and the FAQ corpora. Overall, we find that our methods work well for the retrieval experiments in the different languages. For English, the use of Google Spelling Suggestions and term expansion strategies improve retrieval scores. For Hindi and Malayalam retrieval experiments, we find that translation of queries and corpus to English increases retrieval accuracy.