Search

There's now an increase in the number of Question Answering communities where large archives of question and answer pairs are collected up over time. These archives help traditional type-specified Question Answering (QA) systems to overcome type constraints and enable a service of general types. Semantic similarity measures between sentences dominate the overall performance of such Archive-based QA systems in finding similar questions in the archive to users' requests. Available approaches to sentence similarity measurement mainly utility word-to-word similarity measures directly in a bag-of-words way. In this paper, we take the syntactic evidence into account and carry out an examination on the impact of syntactic information on the sentence similarity measurement. We also compare the performance of our syntactic information incorporated approach with some baseline retrieval models. Experiments show that our approach outperforms other models both in mean average precision (MAP) and recall. [ABSTRACT FROM AUTHOR]

The technology of data mining is more important in recent years, and it is generally applied to commercial forecast and decision supports. Sequential pattern mining algorithms in the field of data mining play one of the important roles. Many of sequential pattern mining algorithms were proposed to improve the efficiency of data mining or save the utility rate of memory. So, our major study tries to improve the efficiency of sequential pattern mining algorithms. We propose a new algorithm - GRS (A Gradational Reduction Approach for Mining Sequential Patterns) which is an efficient algorithm of mining sequential patterns. GRS algorithm uses gradational reduction mechanism to reduce the length of transactions and uses GraDec function to avoid generating large number of infrequent sequential patterns; and it is very suitable to mine the transactions of databases whose record lengths are very long. The GRS algorithm only generates some sequences which are very possible to be frequent. So, the GRS algorithm can decrease a large number of infrequent sequences and increase the utility rate of memory. [ABSTRACT FROM AUTHOR]

This paper presents a multi-dependency language modeling approach to information retrieval. The approach extends the basic KL-divergence retrieval approach by introducing the hybrid dependency structure, which includes syntactic dependency, syntactic proximity dependency and co-occurrence dependency, to describe dependencies between terms. Term and dependency language models are constructed for both document and query. The relevant between a document and a query is then evaluated by using the KL-divergence between their corresponding models. The new dependency retrieval model has been compared with other traditional retrieval models. Experiment results indicate that it produces significant improvements in retrieval effectiveness. [ABSTRACT FROM AUTHOR]

Study on biological sequence database similarity searching has received substantial attention in the past decade, especially after the sequencing of the human genome. As a result, with larger and larger increases in database sizes, fast similarity search is becoming an important issue. Transforming sequences into numerical vectors, called sequence descriptors, for storing in a multidimensional data structure is becoming a promising method for indexing bio-sequences. In this paper, we present an effective sequence transformation method, called SD (Sequence Descriptor) which uses multiple features of a sequence including Count, RPD (Relative Position Dispersion), and APD (Absolute Position Dispersion) to represent the original sequence data. In contrast to the q-gram transformation method, this avoids the problem of exponentially growing vector size. Also, we present a transformation, called ST (Segment Transformation), which recursively divides sequence data into equal length subsequences, and concatenates them after transformation of the subsequences. Experiments on human genome data show that our transformation method is more effective than the q-gram transformation method. Keywords: Bio-sequence, Sequence Descriptor, Similarity Searching, KNN. [ABSTRACT FROM AUTHOR]

This paper presents a domain-independent approach for partitioning text documents into a set of topic-coherent segment units, where the structure of segments reflects the patterns of sub-topics of the processed text document. The approach adopts similarity analyses, which is based on Shannon Information Theory, to determine topic distribution among text documents without incorporating thesaurus information and other auxiliary knowledge bases. It first observes the documents in terms of consistency of distribution from the viewpoint of individual word and then constructs a number of segmentation proposals accordingly. Furthermore, it employs the K-means clustering technique to get a consensus from these proposals and finally partition text into a set of topic coherent paragraphs. Through extensive experimental studies based on real and synthetic data sources, the performance analysis illustrates the effectiveness of the approach in text segmentation. Keywords: Text segmentation, Shannon Information Theory, K-means. [ABSTRACT FROM AUTHOR]

The explosive growth of World Wide Web has already made it the biggest image repository. Despite some image search engines provide con-venient access to web images, they frequently yield unwanted results. Locating needed and relevant images remains a challenging task. This paper proposes a novel ranking model named EagleRank for web image search engine. In EagleRank, multiple sources of evidence related to the images are considered, including image surrounding text passages, terms in special HTML tags, website types of the images, the hyper-textual structure of the web pages and even the user feedbacks. Meanwhile, the flexibility of EagleRank allows it to combine other potential factors as well. Based on inference network model, EagleRank also gives sufficient support to Boolean AND and OR operators. Our experimental results indicate that EagleRank has better performance than traditional approaches considering only the text from web pages. Keywords: EagleRank, inference network, image search engine, World Wide Web, relevance feedback. [ABSTRACT FROM AUTHOR]

Seven-transmembrane receptors (7TMRs) comprise a large family of membrane-bound proteins that share a unifying signal transduction mechanism (i.e., upon activation, these receptors signal through G proteins). These receptors are involved in a vast variety of physiological functions, including neurotransmission, function of exocrine and endocrine glands, smell, taste, vision, chemotaxis, embryogenesis, development, human immunodeficiency virus (HIV) infection, oncogenesis, cell growth, and differentiation. More recent studies indicate that these receptors are also associated with and signal through other molecules (1). Therefore, it is more appropriate to use the term 7TMR than G protein-coupled receptors (GPCRs). [ABSTRACT FROM AUTHOR]