Multi task learning and incorporating common sense knowledge for question answering

Question Answering (QA) system is an automated approach to retrieve correct responses to the questions asked by human in natural language. Reading comprehension (RC)in contrast to information retrieval, requires integrating information and reasoning about events, entities, and their relations across a full document. Immense progress has been made in the recent years for this task, since the advent of deep learning and use of sequence to sequence models for NLP. This thesis deals with two complex tasks in Question Answering with their own inherent challenges: Multi Task Learning for Narrative Question Answering, which involves developing models to deal with the complexity of the domain of stories, movie scripts and human written answers, and second task is to develop novel ways of incorporating common sense knowledge from external knowledge bases for automated question answering. The models developed for these tasks help to advance research in the area of question answering and highlights some of the shortcomings of the methods proposed in literature.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2019

Author dc:creator

• Agarwal, Dhruv

Contributors dc:contributor

• Hockenmaier, Julia

• NLP,Question Answering, Deep Learning, narrativeQA, common sense

Statement dc:rights

• Copyright 2019 Dhruv Agarwal

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/104919

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/104919