Paper Info
Title
A new passage ranking algorithm for video question answering
Abstract
Developing a question answering (Q/A) system involves in integrating abundant linguistic resources such as syntactic parsers, named entity recognizers which are not only impose time cost but also unavailable in other languages. Ranking-based approaches take the advantage of both efficiency and multilingual portability but most of them bias to high frequent words. In this paper, we propose a new passage ranking algorithm for extending textQ/A toward videoQ/A based on searching lexical information in videos. This method takes both N-gram match and word density into account and finds the optimal match sequence using dynamic programming techniques. Besides, it is very efficient to handle real time tasks for online video question answering. We evaluated our method with 150 actual user's questions on the 45GB video collections. Nevertheless, four well-known but multilingual portable ranking approaches were adopted to compare. Experimental results show that our method outperforms the second best approach with relatively 25.64% MRR score.
Year
DOI
Venue
2006
10.1007/11949534_56
PSIVT
Keywords
Field
DocType
n-gram match,time cost,real time task,optimal match sequence,online video question answering,new passage,video collection,ranking algorithm,question answering,multilingual portable ranking approach,multilingual portability,real time
Dynamic programming,Question answering,Ranking,Computer science,Algorithm,Image processing,Optical character recognition,Artificial intelligence,Natural language processing,Software portability,Parsing,Syntax
Conference
Volume
ISSN
ISBN
4319
0302-9743
3-540-68297-X
Citations 
PageRank 
References 
4
0.48
22
Authors
4
Name
Order
Citations
PageRank
Yu-Chieh Wu124723.16
Yue-Shi Lee254341.14
Jie-Chi Yang335043.91
Show-Jane Yen4537130.05