The Experts below are selected from a list of 306 Experts worldwide ranked by ideXlab platform
Jiechi Yang - One of the best experts on this subject based on the ideXlab platform.
-
A weighted String Pattern matching-based passage ranking algorithm for video question answering
Expert Systems with Applications, 2008Co-Authors: Jiechi Yang, Yue-shi LeeAbstract:Video question answering aims to pinpoint answers in response to user's specified questions. However, most question answering technologies involve in integrating rich specific external knowledge such as syntactic parsers, which are often unavailable for many languages. In this paper, we present a new String Pattern matching-based passage ranking algorithm for extending traditional text Q/A toward videoQ/A. Users interact with our videoQ/A system through natural language questions whereas our system returns three sentence-length passages with corresponding video clips as answers. We collect 45GB Discovery videos and 253 Chinese questions for evaluation. The experimental results showed that our method outperformed six top-performed ranking models. It is 7.39% better than the second best method (language model-based) in relatively MRR score and 6.12% in precision rate. Besides, we also show that the use of a trained Chinese word segmentation tool did decrease the overall videoQ/A performance where most ranking algorithms dropped at least 10% in relatively MRR, precision, and answer Pattern recall rates.
-
toward multimedia a String Pattern based passage ranking model for video question answering
North American Chapter of the Association for Computational Linguistics, 2007Co-Authors: Jiechi YangAbstract: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. We collect 75.6 hours videos and 253 Chinese questions for evaluation. The experimental results showed that our method outperformed six top-performed ranking models. It is 10.16% better than the second best method (language model) in relatively MRR score and 6.12% in precision rate. Besides, we also show that the use of a trained Chinese word segmentation tool did decrease the overall videoQA performance where most ranking algorithms dropped at least 10% in relatively MRR, precision, and answer Pattern recall rates.
-
HLT-NAACL - Toward Multimedia: A String Pattern-Based Passage Ranking Model for Video Question Answering
2007Co-Authors: Jiechi YangAbstract: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. We collect 75.6 hours videos and 253 Chinese questions for evaluation. The experimental results showed that our method outperformed six top-performed ranking models. It is 10.16% better than the second best method (language model) in relatively MRR score and 6.12% in precision rate. Besides, we also show that the use of a trained Chinese word segmentation tool did decrease the overall videoQA performance where most ranking algorithms dropped at least 10% in relatively MRR, precision, and answer Pattern recall rates.
Nikola Kasabov - One of the best experts on this subject based on the ideXlab platform.
-
neural networks letter to spike or not to spike a probabilistic spiking neuron model
Neural Networks, 2010Co-Authors: Nikola KasabovAbstract:Spiking neural networks (SNN) are promising artificial neural network (ANN) models as they utilise information representation as trains of spikes, that adds new dimensions of time, frequency and phase to the structure and the functionality of ANN. The current SNN models though are deterministic, that restricts their applications for large scale engineering and cognitive modelling of stochastic processes. This paper proposes a novel probabilistic spiking neuron model (pSNM) and suggests ways of building pSNN for a wide range of applications including classification, String Pattern recognition and associative memory. It also extends previously published computational neurogenetic models.
-
String Pattern recognition using evolving spiking neural networks and quantum inspired particle swarm optimization
International Conference on Neural Information Processing, 2009Co-Authors: Haza Nuzly Abdull Hamed, Nikola Kasabov, Zbynek Michlovský, Siti Mariyam ShamsuddinAbstract:This paper proposes a novel method for String Pattern recognition using an Evolving Spiking Neural Network (ESNN) with Quantum-inspired Particle Swarm Optimization (QiPSO). This study reveals an interesting concept of QiPSO by representing information as binary structures. The mechanism optimizes the ESNN parameters and relevant features using the wrapper approach simultaneously. The N-gram kernel is used to map Reuters String datasets into high dimensional feature matrix which acts as an input to the proposed method. The results show promising String classification results as well as satisfactory QiPSO performance in obtaining the best combination of ESNN parameters and in identifying the most relevant features.
-
ICONIP (2) - String Pattern Recognition Using Evolving Spiking Neural Networks and Quantum Inspired Particle Swarm Optimization
Neural Information Processing, 2009Co-Authors: Haza Nuzly Abdull Hamed, Nikola Kasabov, Zbynek Michlovský, Siti Mariyam ShamsuddinAbstract:This paper proposes a novel method for String Pattern recognition using an Evolving Spiking Neural Network (ESNN) with Quantum-inspired Particle Swarm Optimization (QiPSO). This study reveals an interesting concept of QiPSO by representing information as binary structures. The mechanism optimizes the ESNN parameters and relevant features using the wrapper approach simultaneously. The N-gram kernel is used to map Reuters String datasets into high dimensional feature matrix which acts as an input to the proposed method. The results show promising String classification results as well as satisfactory QiPSO performance in obtaining the best combination of ESNN parameters and in identifying the most relevant features.
Ayumi Shinohara - One of the best experts on this subject based on the ideXlab platform.
-
String Pattern discovery
Lecture Notes in Computer Science, 2004Co-Authors: Ayumi ShinoharaAbstract:Finding a good Pattern which discriminates one set of Strings from the other set is a critical task in knowledge discovery. In this paper, we review a series of our works concerning with the String Pattern discovery. It includes theoretical analyses of learnabilities of some Pattern classes, as well as development of practical data structures which support efficient String processing.
-
ALT - String Pattern Discovery
Lecture Notes in Computer Science, 2004Co-Authors: Ayumi ShinoharaAbstract:Finding a good Pattern which discriminates one set of Strings from the other set is a critical task in knowledge discovery. In this paper, we review a series of our works concerning with the String Pattern discovery. It includes theoretical analyses of learnabilities of some Pattern classes, as well as development of practical data structures which support efficient String processing.
-
A String Pattern regression algorithm and its application to Pattern discovery in long introns.
Genome informatics. International Conference on Genome Informatics, 2002Co-Authors: Hideo Bannai, Ayumi Shinohara, Shunsuke Inenaga, Masayuki Takeda, Satoru MiyanoAbstract:We present a new approach to Pattern discovery called String Pattern regression, where we are given a data set that consists of a String attribute and an objective numerical attribute. The problem is to find the best String Pattern that divides the data set in such a way that the distribution of the numerical attribute values of the set for which the Pattern matches the String attribute, is most distinct, with respect to some appropriate measure, from the distribution of the numerical attribute values of the set for which the Pattern does not match the String attribute. By solving this problem, we are able to discover, at the same time, a subset of the data whose objective numerical attributes are significantly different from rest of the data, as well as the splitting rule in the form of a String Pattern that is conserved in the subset. Although the problem can be solved in linear time for the subString Pattern class, the problem is NP-hard in the general case (i.e. more complex Patterns), and we present an exact but efficient branch-and-bound algorithm which is applicable to various Pattern classes. We apply our algorithm to intron sequences of human, mouse, fly, and zebrafish, and show the practicality of our approach and algorithm. We also discuss possible extensions of our algorithm, as well as promising applications, such as microarray gene expression data.
-
Speeding Up String Pattern Matching by Text Compression: The Dawn of a New Era
2001Co-Authors: Masayuki Takeda, Ayumi Shinohara, Yusuke Shibata, Tetsuya Matsumoto, Takuya Kida, Shuichi Fukamachi, Takeshi Shinohara, Setsuo ArikawaAbstract:††,☆ † † † †† †† † This paper describes our recent studies on String Pattern matching in compressed texts mainly from practical viewpoints. The aim is to speed up the String Pattern matching task, in comparison with an ordinary search over the original texts. We have successfully developed (1) an AC type algorithm for searching in Huffman encoded files, and (2) a KMP type algorithm and (3) a BM type algorithm for searching in files compressed by the so-called byte pair encoding (BPE). Each of the algorithms reduces the search time at nearly the same rate as the compression ratio. Surprisingly, the BM type algorithm runs over BPE compressed files about 1.2–3.0 times faster than the exact match routines of the software package agrep, which is known as the fastest Pattern matching tool.
Solon P. Pissis - One of the best experts on this subject based on the ideXlab platform.
-
Tree template matching in ranked ordered trees by pushdown automata
Journal of Discrete Algorithms, 2012Co-Authors: Tomas Flouri, Bořivoj Melichar, Jan Janousek, Costas S. Iliopoulos, Solon P. PissisAbstract:We consider the problem of tree template matching in ranked ordered trees, and propose a solution based on the bottom-up technique. Specifically, we transform the tree Pattern matching problem to a String matching problem, by transforming the tree template and the subject tree to Strings representing their postfix notation, and then use pushdown automata as the computational model. The method is analogous to the construction of String Pattern matchers. The given tree template is preprocessed once, by constructing a nondeterministic pushdown automaton, which is then transformed to the equivalent deterministic one. Although we prove that the space required for preprocessing is exponential to the size of the tree template in the worst case, the space required for a specific class of tree templates is linear. The time required for the searching phase is linear to the size of the subject tree in both cases.
-
CIAA - Tree template matching in ranked ordered trees by pushdown automata
Implementation and Application of Automata, 2011Co-Authors: Tomas Flouri, Bořivoj Melichar, Jan Janousek, Costas S. Iliopoulos, Solon P. PissisAbstract:We consider the problem of tree template matching in ranked ordered trees, and propose a solution based on the bottom-up technique. Specifically, we transform the tree Pattern matching problem to a String matching problem, by transforming the tree template and the subject tree to Strings representing their postfix notation, and then use pushdown automata as the computational model. The method is analogous to the construction of String Pattern matchers. The given tree template is preprocessed once, by constructing a nondeterministic pushdown automaton, which is then transformed to the equivalent deterministic one. Although we prove that the space required for preprocessing is exponential to the size of the tree template in the general case, the space required for a specific class of tree templates is linear. The time required for the searching phase is linear to the size of the subject tree in both cases.
Yue-shi Lee - One of the best experts on this subject based on the ideXlab platform.
-
A weighted String Pattern matching-based passage ranking algorithm for video question answering
Expert Systems with Applications, 2008Co-Authors: Jiechi Yang, Yue-shi LeeAbstract:Video question answering aims to pinpoint answers in response to user's specified questions. However, most question answering technologies involve in integrating rich specific external knowledge such as syntactic parsers, which are often unavailable for many languages. In this paper, we present a new String Pattern matching-based passage ranking algorithm for extending traditional text Q/A toward videoQ/A. Users interact with our videoQ/A system through natural language questions whereas our system returns three sentence-length passages with corresponding video clips as answers. We collect 45GB Discovery videos and 253 Chinese questions for evaluation. The experimental results showed that our method outperformed six top-performed ranking models. It is 7.39% better than the second best method (language model-based) in relatively MRR score and 6.12% in precision rate. Besides, we also show that the use of a trained Chinese word segmentation tool did decrease the overall videoQ/A performance where most ranking algorithms dropped at least 10% in relatively MRR, precision, and answer Pattern recall rates.
