作者: Partha Pakray , Santanu Pal , Soujanya Poria , Sivaji Bandyopadhyay , Alexander Gelbukh
DOI: 10.1007/978-3-642-37798-3_4
关键词:
摘要: The paper describes an SMS-based FAQ retrieval system. goal of this task is to find a question Q* from corpora FAQs (Frequently Asked Questions) that best answers or matches the SMS query S. test corpus used in contained three languages: English, Hindi and Malayalam. were several domains, including railway enquiry, telecom, health banking. We first checked using Bing spell-checker. Then we unigram matching, bigram 1-skip matching modules for monolingual retrieval. For cross-lingual system, following modules: SMS-to-English translation English-to-Hindi