SMS-Based FAQ Retrieval

FIRE 2011 Task


Home
Dataset
Important Dates
People
Submission
Attendance
Resources
Contact
Results
Joint Task Coordinators
COER
and
IBM Research

Dataset

The FAQs have been collected from online sites - both government and private. The FAQs are in three languages:

  • English
  • Hindi
  • Malayalam

The FAQs are from several domains, including:

  • Railway Enquiry
  • Telecom
  • Health
  • Banking

The SMSes have been generated by asking college students to write down their information need using a mobile phone.

To participate register by sending an email to fire2011smstask@gmail.com and download the dataset and open it using the password that will be provided to you upon registering.

The following datasets have been released till date:

Preview Dataset: Release Date: May 18, 2011

Training Dataset: Release Date: July 7, 2011

Test Dataset: Release Date: Aug 16, 2011

Test Dataset with matches: Release Date: Nov 15, 2011

Java Program (Source code) : Evaluate your results: Release Date: Feb 07, 2012