Wei-Pang Yang

Text summarization using a trainable summarizer and latent semantic analysis

This paper proposes two approaches to address text summarization: modified corpus-based approach (MCBA) and LSA-based T.R.M. approach (LSA + T.R.M.). The first is a trainable summarizer, which takes into account several features, including position, positive keyword, negative keyword, centrality, and the resemblance to the title, to generate summaries. Two new ideas are exploited: (1) sentence positions are ranked to emphasize the significances of different sentence positions, and (2) the score function is trained by the genetic algorithm (GA) to obtain a suitable combination of feature weights. The second uses latent semantic analysis (LSA) to derive the semantic matrix of a document or a corpus and uses semantic sentence representation to construct a semantic text relationship map. We evaluate LSA + T.R.M. both with single documents and at the corpus level to investigate the competence of LSA in text summarization. The two novel approaches were measured at several compression rates on a data corpus composed of 100 political articles. When the compression rate was 30%, an average f-measure of 49% for MCBA, 52% for MCBA + GA, 44% and 40% for LSA + T.R.M. in single-document and corpus level were achieved respectively.

A discretization algorithm based on Class-Attribute Contingency Coefficient

Discretization algorithms have played an important role in data mining and knowledge discovery. They not only produce a concise summarization of continuous attributes to help the experts understand the data more easily, but also make learning more accurate and faster. In this paper, we propose a static, global, incremental, supervised and top-down discretization algorithm based on Class-Attribute Contingency Coefficient. Empirical evaluation of seven discretization algorithms on 13 real datasets and four artificial datasets showed that the proposed algorithm could generate a better discretization scheme that improved the accuracy of classification. As to the execution time of discretization, the number of generated rules, and the training time of C5.0, our approach also achieved promising results.

Answering heterogeneous database queries with degrees of uncertainty

In heterogeneous database systems,partial values have been used to resolve some schema integration problems. Performing operations on partial values may producemaybe tuples in the query result which cannot be compared. Thus, users have no way to distinguish which maybe tuple is the most possible answer. In this paper, the concept of partial values is generalized toprobabilistic partial values. We propose an approach to resolve the schema integration problems using probabilistic partial values and develop a full set of extended relational operators for manipulating relations containing probabilistic partial values. With this approach, the uncertain answer tuples of a query are associated with degrees of uncertainty (represented by probabilities). That provides users a comparison among maybe tuples and a better understanding on the query results. Besides, extended selection and join are generalized to α-selection and α-join, respectively, which can be used to filter out maybe tuples with low probabilities — those which have probabilities smaller than α.

A communication-efficient three-party password authenticated key exchange protocol

Three-party password authenticated key exchange (3PAKE) protocols allow two users (clients) to establish a session key through an authentication server over an insecure channel. Clients only share an easy-to-remember password with the trusted server. In the related literature, most schemes employ the server public keys to ensure the identities of both the servers and symmetric cryptosystems to encrypt the messages. This paper describes an efficient 3PAKE based on LHL-3PAKE proposed by Lee et al. Our 3PAKE requires neither the server public keys nor symmetric cryptosystems such as DES. The formal proof of security of our 3PAKE is based on the computational Diffie-Hellman assumption in the random oracle model along with a parallel version of the proposed 3PAKE. The comparisons have shown that our 3PAKE is more practical than other 3PAKEs.

Classifier design with feature selection and feature extraction using layered genetic programming

This paper proposes a novel method called FLGP to construct a classifier device of capability in feature selection and feature extraction. FLGP is developed with layered genetic programming that is a kind of the multiple-population genetic programming. Populations advance to an optimal discriminant function to divide data into two classes. Two methods of feature selection are proposed. New features extracted by certain layer are used to be the training set of next layers populations. Experiments on several well-known datasets are made to demonstrate performance of FLGP.

Byzantine agreement in the presence of mixed faults on processors and links

In early stage, the Byzantine agreement (BA) problem was studied with single faults on processors in either a fully connected network or a nonfully connected network. Subsequently, the single fault assumption was extended to mixed faults (also referred to as hybrid fault model) on processors. For the case of both processor and link failures, the problem has been examined in a fully connected network with a single faulty type, namely an arbitrary fault. To release the limitations of a fully connected network and a single faulty type, the problem is reconsidered in a general network. The processors and links in such a network can both be subjected to different types of fault simultaneously. The proposed protocol uses the minimum number of message exchanges and can tolerate the maximum number of allowable faulty components to make each fault-free processor reach an agreement.

Controlling access in large partially ordered hierarchies using cryptographic keys

The problem of access control in a hierarchy is present in many application areas. Since computing resources have grown tremendously, access control is more frequently required in areas such as computer networks, database management systems, and operating systems. Many schemes based on cryptography have been proposed to solve this problem. However, previous schemes need large values associated with each security class. In this paper, we propose a new scheme to solve this problem achieving the following two goals. One is that the number of keys is reduced without affecting the security of the system. The other goal is that when a security class is added to the system, we need only update a few keys of the related security classes with simple operations.

Designing a classifier by a layered multi-population genetic programming approach

This paper proposes a method called layered genetic programming (LAGEP) to construct a classifier based on multi-population genetic programming (MGP). LAGEP employs layer architecture to arrange multiple populations. A layer is composed of a number of populations. The results of populations are discriminant functions. These functions transform the training set to construct a new training set. The successive layer uses the new training set to obtain better discriminant functions. Moreover, because the functions generated by each layer will be composed to a long discriminant function, which is the result of LAGEP, every layer can evolve with short individuals. For each population, we propose an adaptive mutation rate tuning method to increase the mutation rate based on fitness values and remaining generations. Several experiments are conducted with different settings of LAGEP and several real-world medical problems. Experiment results show that LAGEP achieves comparable accuracy to single population GP in much less time.

Authenticated encryption schemes with message linkage

Authenticated encryption schemes need redundancy schemes to link up the message blocks; however, these redundancies increase communication costs. To construct links without increasing communication costs, we propose a general solution for all the authenticated encryption schemes based on the discrete logarithm problem. Because the computation cost to construct links is small, the improved scheme adopting our solution is almost as efficient as the original one. Moreover, by our solution, the recipient can easily determine the missing message blocks, and then acknowledge the sender to send only these blocks again. The communication cost will be also reduced. Adopting our solution, we also propose two new authenticated encryption schemes with message linkage.

iSpreadRank: Ranking sentences for extraction-based summarization using feature weight propagation in the sentence similarity network

Sentence extraction is a widely adopted text summarization technique where the most important sentences are extracted from document(s) and presented as a summary. The first step towards sentence extraction is to rank sentences in order of importance as in the summary. This paper proposes a novel graph-based ranking method, iSpreadRank, to perform this task. iSpreadRank models a set of topic-related documents into a sentence similarity network. Based on such a network model, iSpreadRank exploits the spreading activation theory to formulate a general concept from social network analysis: the importance of a node in a network (i.e., a sentence in this paper) is determined not only by the number of nodes to which it connects, but also by the importance of its connected nodes. The algorithm recursively re-weights the importance of sentences by spreading their sentence-specific feature scores throughout the network to adjust the importance of other sentences. Consequently, a ranking of sentences indicating the relative importance of sentences is reasoned. This paper also develops an approach to produce a generic extractive summary according to the inferred sentence ranking. The proposed summarization method is evaluated using the DUC 2004 data set, and found to perform well. Experimental results show that the proposed method obtains a ROUGE-1 score of 0.38068, which represents a slight difference of 0.00156, when compared with the best participant in the DUC 2004 evaluation.