Automatic Question-Answering System for Factoid & Non-Factoid Open-Domain Questions


Mariia Khvalchik

Oral Defence Date: 

Thursday, May 11, 2017 - 12:30


TH 434


Assist. Prof Anagha Kulkarni, Assoc. Prof. Hui Yang, & Prof. Dragutin Petkovic


We present an end-to-end system for open-domain non-factoid question-answering that consists of three components. (1) The query formulation module is tasked with transforming the verbose, and often non-grammatical and noisy question into a boolean query of few keywords. The generated query is then run through a commercial search engine to obtain matching documents from the Web. (2) The candidate answer generation module extracts potential answers from the retrieved documents. (3) The answer selection module is responsible for identifying the best answer based on various criteria. A thorough empirical evaluation using multiple datasets demonstrates that the proposed approach is highly competitive.

Mariia Khvalchik

Question Answering, Machine Learning, Neural Networks, Natural Language Processing.