Fabien Bouskila, William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing. In Proceedings of the 2000 International Conference on Artificial Intelligence (IC-AI 2000), Las Vegas, Nevada, June, 2000.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....extraction. 3.1 Terminology Before we introduce the functional parts of the system, we must introduce some terminology: ffl Items: Item refers to the basic unit of data content that is used in textual data mining. We generally use item to refer to a single document; however as explained in [2], other units of information, such as subsections of a document or sentences, could be used as well. For simplicity we will assume that item refers to a document in this article. ffl Collections: A collection refers to a group of items that will be indexed in the HDDI system. ffl Concepts: We ....

F. Bouskila. The role of semantic locality in hierarchical distributed dynamic indexing and information retrieval. Master 's thesis, University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering, 1999.

....of Semantic Locality The resulting weight assignments from knowledge base creation are context sensitive. We use these weights to determine regions of semantic locality (i.e. conceptual density) within each collection. We then detect clusters of concepts within a knowledge base [BP00] [B99], T72] The result is a knowledge base consisting of regions of high density clusters of concepts subtopic regions of semantic locality. These regions consist of clusters of concepts that commonly appear together and collectively create a knowledge neighborhood. Our premise is that we can ....

F. D. Bouskila, The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing and Information Retrieval, M.S. Thesis, Department of Electrical and Computer Engineering at the University of Illinois at UrbanaChampaign, December (Bouskila's thesis work was supervised by William M. Pottenger).

....(Section 3.3) for detecting emerging trends. Chapter 6 presents conclusions as well as the project s future plans. 2.0 Motivation and Related Work In previous work, 3, 9, 10] we examined the usage of various linguistic and statistical features to track trends across time. The HDDI TM system [4,14] is used to extract linguistic features from a repository of textual data and to generate clusters based on the semantic similarity of these features. The rate of change in the size of clusters and in the frequency and association of features is used as input to machine learning techniques to ....

....mechanism, which tracks topical information in a stream consisting of news stories using speech processing technology. The goal of [8] is essentially to detect changes in topics disruptive events exhibiting discontinuities in semantics in localized data sources such as newscasts. Our research [3, 4, 9, 10] focuses on integrative or non disruptive emergence of topics that build on previously existing topics. There is a significant difference in the goal of these research projects: unlike the TDT research, our goal is to detect novel trends that are globally incipient in a given domain. TimeMines ....

[Article contains additional citation context not shown here]

Fabien Bouskila, William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing. In Proceedings of the 2000.

No context found.

Fabien Bouskila and William M. Pottenger, "The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing", Proceedings of the 2000.

No context found.

Bouskila, F. D. and William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing. In the Proceedings of the International Conference on Artificial Intelligence (ICAI '2000.

....Relay Chat) could benefit from utilizing such a tool. 1. 1 Modeling Social Semantic Relations The application under development at Lehigh University to model social and semantic interactions is the Social Semantic Builder (SSB) The SSB is a relational modeling tool that utilizes the HDDI [6][2][1] text mining infrastructure, and models relationships between distinct conceptual and or behavioral abstractions. The purpose of the SSB is to determine, analyze, and model the relationships and interactions between these abstract relational entities. As an example, consider the domain of ....

Bouskila, F.D. and William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed. Dynamic Indexing. Proceedings of the InternationalConference on Artificial Intelligence (IC-AI'2000), Las Vegas, NV, June.

....of both social and semantic relations within chat data. 3. 0 Modeling Social and Semantic Relations The application under development at Lehigh University to model social and semantic interactions is the Social Semantic Builder (SSB) The SSB is a relational modeling tool that utilizes HDDI [13][2][1] text mining infrastructure, and models inherent relationships between distinct conceptual and or behavioral abstractions. The purpose of the SSB is to determine, analyze, and model the relationships and interactions between these abstract relational entities. As an example, consider the ....

....multiple authors and content (such as chat) 3. 1 Approach to Modeling Semantic Relations Within the semantic domain, our methodology utilizes contextual transitivity in the co occurrence relation to identify regions of high density concept clusters or subtopic regions of semantic locality [2]. The regions of semantic locality are based on higherorders of co occurrence in the co occurrence relation [19] These regions consist of clusters of concepts that commonly appear together and collectively create a knowledge neighborhood. The premise is that grouping similar concepts together ....

[Article contains additional citation context not shown here]

Bouskila, F.D. and William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing. Proceedings of the International Conference on Artificial Intelligence (IC-AI'2000), Las Vegas, NV, June.

....Science education. CIMEL is a multimedia framework for constructive and collaborative, inquiry based learning. 2.0 Related Work and Motivation In our previous work, 3, 9, 10, 13] we examined the usage of various linguistic and statistical features to track trends across time. The HDDI TM system [4,14] is used to extract linguistic features from a repository of textual data and to generate clusters based on the semantic similarity of these features. The rate of change in the size of clusters and in the frequency and association of features is used as input to machine learning techniques to ....

....Tracking mechanism, which tracks topical information in a stream consisting of news stories using speech processing. The goal of [8] is essentially to detect changes in topics disruptive events exhibiting discontinuities in semantics in localized data sources such as newscasts. Our research [3, 4, 9, 10] focuses on integrative or non disruptive emergence of topics that build on previously existing topics. There is a significant difference in the goal of these research projects: unlike the TDT research, our goal is to detect novel trends that are globally incipient in a given domain. TimeMines ....

[Article contains additional citation context not shown here]

Fabien Bouskila, William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing. In Proceedings of the 2000.

....of the variety of applications in which the techniques can be applied. Technology forecasting, as a specific example, employs collections of trade, technical, and patent literature. Such collections are partitioned into topical domains of knowledge that we refer to as regions of semantic locality [2]. These topical domains of knowledge are traced over time to detect emerging trends in conceptual content. The process of detecting emerging conceptual content that we envision is analogous to the operation of a radar system. A radar system assists in the differentiation of mobile vs. stationary ....

....(i.e. conceptual den Note that follow on work that builds on [10] terms this a Concept Space 2001 4 23 i i i i i i 4 6 1 5 2 R2 R3 Figure 2. An Example Application of Tarjan s Algorithm sity) within each collection. We thus detect clusters of concepts within a knowledge base [2], 12] 13] The result is a knowledge base consisting of regions of high density clusters of concepts: i.e. subtopic regions of semantic locality. These regions consist of clusters of concepts that commonly appear together and collectively create a knowledge neighborhood. Our premise is that ....

[Article contains additional citation context not shown here]

F. D. Bouskila and W. M. Pottenger, The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing, Proceedings of the International Conference on Artificial Intelligence (IC-AI'2000.

....of Regions of Semantic Locality The resulting weight assignments from knowledge base creation are context sensitive. We use these weights to determine regions of semantic locality (i.e. conceptual density) within each collection. We then detect clusters of concepts within a knowledge base [BP00], B99] T72] The result is a knowledge base consisting of regions of high density clusters of concepts subtopic regions of semantic locality. These regions consist of clusters of concepts that commonly appear together and collectively create a knowledge neighborhood. Our premise is that we ....

....clusters of concepts subtopic regions of semantic locality. These regions consist of clusters of concepts that commonly appear together and collectively create a knowledge neighborhood. Our premise is that we can impute a constrained, contextual transitivity to the co occurrence relation [BP00], thereby forming regions of semantic locality (see illustration on the right in section 4 above) The motivation for the use of the term semantic locality comes from the commonly applied premise that grouping similar concepts together leads to increased effectiveness and efficiency in query ....

[Article contains additional citation context not shown here]

F. D. Bouskila and William M. Pottenger, The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing, Proceedings of the International Conference on Artificial Intelligence (IC-AI2000), Las Vegas, NV, June.

No context found.

Fabien Bouskila, William M. Pottenger. The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing. In Proceedings of the 2000 International Conference on Artificial Intelligence (IC-AI 2000), Las Vegas, Nevada, June, 2000.

No context found.

F. D. Bouskila, "The Role of Semantic Locality in Hierarchical Distributed Dynamic Indexing and Information Retrieval", MS thesis, University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering, 1999. (Thesis advisor was William M. Pottenger, Ph.D.)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC