Loading...

An Open Domain Question Answering Method Based on Document Categorization

Anvari, Hamid Reza | 2011

558 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 41901 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Abolhassani, Hassan
  7. Abstract:
  8. One of the new paradigms in information retrieval is to develop textual Question-Answering systems. Question-Answering (QA) is an advanced IR process at which for a natural language question, the answer is extracted and issued in natural language. The QA systems are divided into two general groups: Open-Domain QA and Restricted-Domain QA.
    In this research field, a number of different models and methods are developed in which a document collection is used to retrieve candidate answers and then different methods are deployed to detect and eliminate irrelevant ones from answer set. Most of these methods decide based on expected semantic answer type, which is determined using pre-defined concepts, taxonomies and ontologies.
    In this Research, we intend to introduce a new model for Open Domain Question Answering (ODQA) based on Text Categorization techniques in order to improve Accuracy and precision. In this process we develop preprocessing steps including a new query-expansion method to handle the challenge of small number of keywords in issued question. We use World Wide Web (WWW) as the document collection along with search engines as base retrieval tools. We’ve also designed the system using component-based model to allow different components get optimized or replaced with new ones without need to change remaining modules in the system
  9. Keywords:
  10. Information Retrieval ; Query Expansion ; Text Categorization ; Open Domain Question Answering

 Digital Object List

 Bookmark

No TOC