1,420 Hits in 5.9 sec

A weighted string pattern matching-based passage ranking algorithm for video question answering

2008 Expert systems with applications  
In this paper, we present a new string pattern matching-based passage ranking algorithm for extending traditional textbased QA toward videoQA.  ...  Users interact with our videoQA system through natural language questions, while our system returns passage fragments with corresponding video clips as answers.  ...  In this paper, we present a new string pattern matching-based passage ranking algorithm for video question answering.  ... 
doi:10.1016/j.eswa.2007.04.008 fatcat:hn7sv3h6ybcqpge5page3rxdii

A Robust Passage Retrieval Algorithm for Video Question Answering

Yu-Chieh Wu, Jie-Chi Yang
2008 IEEE transactions on circuits and systems for video technology (Print)  
In this paper, we present a robust passage retrieval algorithm to extend the conventional text question answering (Q/A) to videos.  ...  Index Terms-Multimedia retrieval, question answering (Q/A), video question answering (videoQ/A).  ...  In this paper, we present a string pattern-based passage ranking algorithm for videoQ/A.  ... 
doi:10.1109/tcsvt.2008.2002831 fatcat:cffpxmodh5b2tau7ga4iovxho4

BVideoQA: Online English/Chinese bilingual video question answering

Yue-Shi Lee, Yu-Chieh Wu, Jie-Chi Yang
2009 Journal of the American Society for Information Science and Technology  
On the basis of the matched string patterns, it gives a passage score based on our term-weighting scheme.  ...  This article presents a bilingual video question answering (QA) system, namely BVideoQA, which allows users to retrieve Chinese videos through English or Chinese natural language questions.  ...  By following the FOSP algorithm, the observed matched strings for the aforementioned example are: String Pattern Weighting After extracting the optimal subsequences, we compute the following score to  ... 
doi:10.1002/asi.21002 fatcat:7oybe2fz6fhupmw2y6dascfs4y

A Survey on Why-Type Question Answering Systems [article]

Manvi Breja, Sanjay Kumar Jain
2019 arXiv   pre-print
Question Answering Systems reduce the time taken to get an answer, to a query asked in natural language by providing the one most relevant answer.  ...  The paper presents a survey on Why-type Question Answering System, details the architecture, the processes involved in the system and suggests further areas of research.  ...  The answer extraction is based on four measures, which are simple matching (finding total weight by summing the weights assigned to stop words and non-stop words appearing in an answer), longest consecutive  ... 
arXiv:1911.04879v1 fatcat:wdvngfqkqvgfvmjn67adebwtqi

An Efficient Passage Ranking Technique For a QA System

Pooja A
2012 International Journal of Computer Science & Information Technology (IJCSIT)  
An important stage of such a system is the passage ranking stage, which ranks the possible answers based on their relevance to the question.  ...  Question answering (QA) systems provide an intuitive way of requesting concise information from a given data source.  ...  ACKNOWLEDGEMENTS We thank A.  ... 
doi:10.5121/ijcsit.2012.4606 fatcat:sgmgva37r5c3lf4nada3r44i2y

FDU at TREC-10: Filtering, QA, Web and Video Tasks

Lide Wu, Xuanjing Huang, Junyu Niu, Yikun Guo, Yingju Xia, Zhe Feng
2001 Text Retrieval Conference  
This year Fudan University takes part in the TREC conference for the second time. We have participated in four tracks of Filtering, Q&A, Web and Video.  ...  In the task of video retrieval, we have submitted the results of 17 topics among all the topics.  ...  We are thankful to Lin Mei, Yuefei Guo, Weixiang Zhao Yi Zheng, Yaqian Zhou, Kaijiang Chen, Xiaoye Lu, Jie Xi, He Ren, Li Lian, Wei Qian, Hua Wan and Tian Hu for their help in the implementation.  ... 
dblp:conf/trec/WuHNGXF01 fatcat:626yugbapjh3bi2j32dp737gjm

Analyzing Analytics

Rajesh Bordawekar, Bob Blainey, Ruchir Puri
2015 Synthesis Lectures on Computer Architecture  
For most major model types, we study implementations of key algorithms to determine common computational and runtime patterns.  ...  We are interested in isolating and documenting repeated patterns in analytical algorithms, data structures and data types, and in understanding how these could be most effectively mapped onto parallel  ...  For example, Watson's key functional goals are: pattern matching for input question analysis, prediction for choosing answers, and simulation for wager and clue selection.  ... 
doi:10.2200/s00678ed1v01y201511cac035 fatcat:jkjywe5rzzaupjwq5rjyavqxi4

A survey on question answering technology from an information retrieval perspective

Oleksandr Kolomiyets, Marie-Francine Moens
2011 Information Sciences  
functions which are used for estimating the relevance between a query and an answer candidate.  ...  This article provides a comprehensive and comparative overview of question answering technology.  ...  [27] studied a fuzzy relation matching technique for factoid passage retrieval.  ... 
doi:10.1016/j.ins.2011.07.047 fatcat:se6dcorj2jbidath35go5wi5yy

New TCDE Chair for 2002-2003

Per-Åke Larson, Masaru Kitsuregawa, Betty Salzberg
2001 IEEE Data Engineering Bulletin  
Papers for each issue are solicited by and should be sent to the Associate Editor responsible for the issue.  ...  Indexing Methods for Approximate String Matching 1 Introduction Approximate string matching is about finding a pattern in a text where the pattern, the text, or both have suffered some kind of undesirable  ...  Hence, we can derive sufficient conditions for an approximate match based on exact matching of one or more carefully selected pattern pieces.  ... 
dblp:journals/debu/LarsonKS01a fatcat:o2p7xdbnj5ctnnvxjwymdiq4gm

A domain-independent approach to finding related entities

Olga Vechtomova, Stephen E. Robertson
2012 Information Processing & Management  
An initial list of candidate entities, extracted from top ranked documents retrieved for the query, is refined using a number of statistical and linguistic methods.  ...  Our research goal is to investigate whether related entity finding problem can be addressed by combining a measure of relatedness of candidate answer entities to the query, and likelihood that the candidate  ...  In order to determine the value for m we took the entity names ranked by the TFIDF for the training topics, and did a simple pattern matching with the correct answer set of entity names.  ... 
doi:10.1016/j.ipm.2011.12.003 fatcat:f7hxlt36e5gw3henruj2ybyuyy

A Survey on Multi-hop Question Answering and Generation [article]

Vaibhav Mavi
2022 arXiv   pre-print
The problem of Question Answering (QA) has attracted significant research interest for long.  ...  The ability to answer multi-hop questions and perform multi step reasoning can significantly improve the utility of NLP systems.  ...  . • Generative answers: For longer sequences of texts, directly matching strings to give a binary score fails to tell which answers are closer to the gold answers.  ... 
arXiv:2204.09140v1 fatcat:tqr6472sjrfpvollvapwo3z3x4

Finding Parallel Passages in Cultural Heritage Archives

Martyn Harris, Mark Levene, Dell Zhang, Dan Levene
2018 ACM Journal on Computing and Cultural Heritage  
In this paper, we present in detail how we build a digital infrastructure that can facilitate the search and discovery of parallel passages for any domain in any language.  ...  Although there exist a few software tools for this purpose, they are restricted to a specific domain (e.g., the Bible) or a specific language (e.g., Hebrew).  ...  The algorithm assigns more weight to snippets containing all of the query n-grams to ensure the snippets are ranked in such a way that the top snippets will contain full matches to the query, before presenting  ... 
doi:10.1145/3195727 fatcat:plgfe4irgnbgjizo5d3lg6hurq

Building Watson: An Overview of the DeepQA Project

David Ferrucci, Eric Brown, Jennifer Chu-Carroll, James Fan, David Gondek, Aditya A. Kalyanpur, Adam Lally, J. William Murdock, Eric Nyberg, John Prager, Nico Schlaefer, Chris Welty
2010 The AI Magazine  
Our results strongly suggest that DeepQA is an effective and extensible architecture that may be used as a foundation for combining, deploying, evaluating and advancing a wide range of algorithmic techniques  ...  The extent of the challenge includes fielding a real-time automatic contestant on the show, not merely a laboratory exercise. The Jeopardy!  ...  It is this team who are responsible for the work described in this paper. From  ... 
doi:10.1609/aimag.v31i3.2303 fatcat:bqzu6kcak5gnhpabvyv6vuc7n4

Context & Semantics in News & Web Search

Daan Odijk
2016 SIGIR Forum  
Each video segment has a unique ID and three associated files (the first two are provided, the last one needs to be reconstructed):  ...  The dataset that was described in Section 6.3 has been made available to the research community; 3 it consists of more than 1,500 manually annotated links in over 5,000 subtitle chunks for 50 video segments  ...  Early work included defining a taxonomy of hyperlink types and applying string-matching methods for automatic links [4] .  ... 
doi:10.1145/2964797.2964816 fatcat:zmt2clavxrdi5izyo73z6kfg3q

Combining structured and unstructured information in a retrieval model for accessing legislation

Marie-Francine Moens
2005 Proceedings of the 10th international conference on Artificial intelligence and law - ICAIL '05  
Such an approach is very promising for the retrieval of legal documents. This is illustrated with two retrieval models specifically designed for the retrieval of legislation.  ...  Current information retrieval research takes into account the structured information content of documents when computing the relevance ranking.  ...  For very specific queries, a single statute article may contain the right answer, whereas more general questions could be answered by returning a whole chapter.  ... 
doi:10.1145/1165485.1165507 dblp:conf/icail/Moens05 fatcat:73tf7wv755ggdcdlbgb7kyqxuy
« Previous Showing results 1 — 15 out of 1,420 results