UNT Scholarly Works - 24 Matching Results

Search Results

Results: 1 - 24
open access

Hybrid Energy-Aware Synchronization Algorithm in Wireless Sensor Networks

Description: This paper discusses a time synchronization scheme for wireless sensor networks that aims to conserve sensor battery power while maintaining network connectivity for as long as possible.
Date: September 2007
Creator: Akl, Robert G. & Saravanos, Yanos
Partner: UNT College of Engineering
open access

Grid-based Coordinated Routing in Wireless Sensor Networks

Description: This paper discusses grid-based coordinated routing in wireless sensor networks and compares the energy available in the network over time for different grid sizes. The authors explore the quality of service of wireless sensor networks, how the coordinator nodes are elected, and the size of the grid area that will minimize the total energy consumption and extend the lifetime of the network.
Date: January 2007
Creator: Akl, Robert G. & Sawant, Uttara
Partner: UNT College of Engineering
open access

The Multidisciplinary Facets of Research on Humour

Description: In this paper, the authors summarize the main theories of humor that emerged from philosophical and modern psychological research, and survey the past and present developments in the fields of theoretical and computational linguistics.
Date: July 2007
Creator: Mihalcea, Rada, 1974-
Partner: UNT College of Engineering
open access

Using Wikipedia for Automatic Word Sense Disambiguation

Description: This paper describes a method for generating sense-tagged data using Wikipedia as a source of sense annotations. Through word sense disambiguation experiments, the authors show that the Wikipedia-based sense annotations are reliable and can be used to construct accurate sense classifiers.
Date: April 2007
Creator: Mihalcea, Rada, 1974-
Partner: UNT College of Engineering
open access

Unsupervised Graph-based Word Sense Disambiguation Using Measures of Word Semantic Similarity

Description: This paper describes an unsupervised graph-based method for word sense disambiguation, and presents comparative evaluations using several measures of word semantic similarity and several algorithms for graph centrality. The results indicate that the right combination of similarity metrics and graph centrality algorithms can lead to a performance competing with the state-of-the-art in unsupervised word sense disambiguation, as measured on standard data sets.
Date: September 2007
Creator: Sinha, Ravi & Mihalcea, Rada, 1974-
Partner: UNT College of Engineering
open access

Random-Walk Term Weighting for Improved Text Classification

Description: This paper describes a new approach for estimating term weights in a document, and shows how the new weighting scheme can be used to improve the accuracy of a text classifier.
Date: September 2007
Creator: Hassan, Samer; Mihalcea, Rada, 1974- & Banea, Carmen
Partner: UNT College of Engineering
open access

Explorations in Automatic Book Summarization

Description: This paper discusses explorations in automatic book summarization.
Date: June 2007
Creator: Ceylan, Hakan & Mihalcea, Rada, 1974-
Partner: UNT College of Engineering
open access

Wikify! Linking Documents to Encyclopedic Knowledge

Description: This paper introduces the use of Wikipedia as a resource for automatic keyword extraction and word sense disambiguation, and shows how this online encyclopedia can be used to achieve state-of-the-art results on both these tasks.
Date: November 2007
Creator: Mihalcea, Rada, 1974- & Csomai, Andras
Partner: UNT College of Engineering
open access

Characterizing Humour: An Exploration of Features in Humorous Texts

Description: This paper investigates the problem of automatic humor recognition, and provides an in-depth analysis of two of the most frequently observed features of humorous text: human-centeredness and negative polarity. Through experiments performed on two collections of humorous texts, the authors show that these properties of verbal humor are consisted across different data sets.
Date: February 2007
Creator: Mihalcea, Rada, 1974- & Pulman, Stephen
Partner: UNT College of Engineering
open access

SemEval-2007 Task 14: Affective Text

Description: The "Affective Text" task focuses on the classification of emotions and valence (positive/negative polarity) in news headlines, and is meant as an exploration of the connection between emotions and lexical semantics. In this paper, the authors describe the data set used in the evaluation and the results obtained by the participating systems.
Date: June 2007
Creator: Strapparava, Carlo, 1962- & Mihalcea, Rada, 1974-
Partner: UNT College of Engineering
open access

UNT: SubFinder: Combining Knowledge Sources for Automatic Lexical Substitution

Description: This paper describes the University of North Texas SubFinder system. The system is able to provide the most likely set of substitutes for a word in a given context, by combining several techniques and knowledge sources. SubFinder has successfully participated in the best and out of ten (oot) tracks in the SEMEVAL lexical substitution task, consistently ranking in the first or second place.
Date: June 2007
Creator: Hassan, Samer; Csomai, Andras; Banea, Carmen; Sinha, Ravi & Mihalcea, Rada, 1974-
Partner: UNT College of Engineering
open access

AC 2007-1844: An Innovative Mechanical and Energy Engineering Curriculum

Description: This paper discusses the addition of a new Department of Mechanical and Energy Engineering at the University of North Texas (UNT). Those involved see the curriculum for this new program as a new model of engineering education that parallels the innovations of UNTs current Learning to Learn (L2L) project-oriented concept course with the addition of innovative approaches for mechanical engineering and emphasis on energy engineering education.
Date: 2007
Creator: Michaelides, Efstathios & Mirshams, Reza
Partner: UNT College of Engineering
open access

A Corpus of Fine-Grained Entailment Relations

Description: This paper describes on-going efforts to annotate a corpus of almost 16,000 answer pairs with an estimated 69,000 fine-grained entailment relationships.
Date: June 2007
Creator: Nielsen, Rodney D. & Ward, Wayne
Partner: UNT College of Engineering
Back to Top of Screen