Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/156955
Title: Open domain question answering system
Authors: Hoang, Nghia Tuyen
Keywords: Engineering::Computer science and engineering::Information systems::Information storage and retrieval
Science::Mathematics
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Hoang, N. T. (2022). Open domain question answering system. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156955
Abstract: Deep learning methods have drawn tremendous attention from both the research community and the industrial practitioners thanks to their undeniable power in learning feature representation in higher dimensions without manual, handcrafting features. An application of deep learning that arises naturally is question answering, in which a question answering system must answer questions posed by humans. One of its sub-fields, opendomain question answering, attempts to answer questions about nearly anything, without being given relevant reference texts. Despite its impactful applications in search engines, chatbots and factual correction, research work in open-domain question answering is relatively under-explored due to its complex and large-scale nature. In this work, we aim to advance the progress of recent open-domain question answering systems by developing various mathematical-driven methods. More specifically, in the first part of this thesis, we introduce the widely adopted two-stage paradigm in opendomain question answering and perform comprehensive error analysis on state-of-the-art models. Based on this, we are then able to formulate and develop methods aiming specifically at overcoming these weaknesses in the second part of the thesis. These approaches range from simple methods such as parameter sharing and data augmentation to more sophisticated methods such as designing new objective functions or pseudo data synthesis and semi-supervised learning. Finally, we unify these developed methods into a single framework that outperforms state-of-the-art models by a significant margin on common benchmarking datasets. The code to reproduce our experiments is released at https://github.com/hnt4499/DPR.
URI: https://hdl.handle.net/10356/156955
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SPMS Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Hoang_Nghia_Tuyen_U1840140F_FYP_Final.pdf
  Restricted Access
1.29 MBAdobe PDFView/Open

Page view(s)

37
Updated on Jun 28, 2022

Download(s)

7
Updated on Jun 28, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.