Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/47344
Title: Multimedia question answering
Authors: NIE LIQIANG
Keywords: Multimedia Question Answering, Question Understanding, Answer Medium Determination, Multimedia Data Selection
Issue Date: 4-Jul-2013
Source: NIE LIQIANG (2013-07-04). Multimedia question answering. ScholarBank@NUS Repository.
Abstract: Along with the proliferation and improvement of underlying search and communication technologies, we have seen a flourishing of automated and community-based question answering services, which have emerged as an effective paradigm for oceanic information seeking, diverse knowledge disseminating, and outstanding expert routing. However, existing QA services provide only textual answers which are not sufficiently intuitive or informative for many questions. On the other hand, the available multimedia data on the Internet has increased exponentially and is likely to increase continuously. Naturally, it is time to shift from traditional textual QA to multimedia QA. It is worth mentioning that multimedia QA has been attracting increasing attentions. Most of the current literatures, however, mainly focus on specific domains and utilize question independent monolithic media type, such as pure video or image, to answer all questions. Therefore, the main aim of this thesis is to design and develop a systematic question-aware multimedia question answering scheme that is able to answer general questions in broad domains with appropriate medium types. Specifically, it covers the studies on question analytics, answer medium determination and multimedia answer selection. Through extensive experiments conducted on the large-scale real-world datasets, the experimental results have demonstrated that our study could yield significant gains in empowering users with concise and intuitive multimedia experiences. As byproducts of this research, the proposed approaches have addressed the question annotation, media search performance prediction as well as web-scale media data reranking with complex queries.
URI: http://scholarbank.nus.edu.sg/handle/10635/47344
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
01NieLQ.pdf4.45 MBAdobe PDF

OPEN

NoneView/Download
02NieLQ.pdf7.73 MBAdobe PDF

OPEN

NoneView/Download
03NieLQ.pdf7.7 MBAdobe PDF

OPEN

NoneView/Download
04NieLQ.pdf2.49 MBAdobe PDF

OPEN

NoneView/Download
05NieLQ.pdf9.68 MBAdobe PDF

OPEN

NoneView/Download
06NieLQ.pdf1.93 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

306
checked on Dec 11, 2017

Download(s)

2,256
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.