You limited your search to:

  Partner: UNT College of Engineering
An Algorithm for Open Text Semantic Parsing

An Algorithm for Open Text Semantic Parsing

Date: August 2004
Creator: Shi, Lei & Mihalcea, Rada, 1974-
Description: Abstract: This paper describes an algorithm for open text shallow semantic parsing. The algorithm relies on a frame dataset (FrameNet) and a semantic network (WordNet), to identify semantic relations between words in open text, as well as shallow semantic features associated with concepts in the text. Parsing semantic structures allows semantic units and constituents to be accessed and processed in a more meaningful way than syntactic parsing, moving the automation of understanding natural language text to a higher level.
Contributing Partner: UNT College of Engineering
The Decomposition of Human-Written Book Summaries

The Decomposition of Human-Written Book Summaries

Date: March 2009
Creator: Ceylan, Hakan & Mihalcea, Rada, 1974-
Description: In this paper, the authors evaluate the extent to which human-written book summaries can be obtained through cut-and-paste operations from the original book. The authors analyze the effect of the parameters involved in the decomposition algorithm, and highlight the distinctions in coverage obtained for different summary types.
Contributing Partner: UNT College of Engineering
Co-training and Self-training for Word Sense Disambiguation

Co-training and Self-training for Word Sense Disambiguation

Date: May 2004
Creator: Mihalcea, Rada, 1974-
Description: This paper investigates the application of co-training and self-training to word sense disambiguation. Optimal and empirical parameter selection methods for co-training and self-training are investigated, with various degrees of error reduction. A new method that combines co-training with majority voting is introduced, with the effect of smoothing the bootstrapping learning curves, and improving the average performance.
Contributing Partner: UNT College of Engineering
Characterizing Humour: An Exploration of Features in Humorous Texts

Characterizing Humour: An Exploration of Features in Humorous Texts

Date: February 2007
Creator: Mihalcea, Rada, 1974- & Pulman, Stephen
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.
Contributing Partner: UNT College of Engineering
Computational Models for Incongruity Detection in Humour

Computational Models for Incongruity Detection in Humour

Date: March 2010
Creator: Mihalcea, Rada, 1974-; Strapparava, Carlo, 1962- & Pulman, Stephen
Description: This paper discusses computational models for incongruity resolution. Abstract: Incongruity resolution is one of the most widely accepted theories of humor, suggesting that humor is due to the mixing of two disparate interpretation frames in one statement. In this paper, the authors explore several computational models for incongruity resolution. The authors introduce a new data set, consisting of a series of 'set-ups' (preparations for a punch line), each of them followed by four possible coherent continuations out of which only one has a comic effect. Using this data set, the authors redefine the task as the automatic identification of the humorous punch line among all the plausible endings. The authors explore several measures of semantic relatedness, along with a number of joke-specific features, and try to understand their appropriateness as computational models for incongruity detection.
Contributing Partner: UNT College of Engineering
Retention and Recruitment of Women in Computer Engineering

Retention and Recruitment of Women in Computer Engineering

Date: July 2006
Creator: Akl, Robert G. & Garlick, Ryan
Description: This presentation discusses strategies and goals for recruiting more women to Computer Science and Engineering degree (CSE) programs at the University of North Texas (UNT). It also describes a series of activities aimed at improving retention rates of women students already in our programs. Such recruitment and retention of women is critical to the country's efforts to increase the number of engineering professionals, and is a priority for the CSE Department at UNT.
Contributing Partner: UNT College of Engineering
Research, Teaching, and Outreach

Research, Teaching, and Outreach

Date: December 2005
Creator: Akl, Robert G.
Description: This presentation discusses research in sensor network routing, WiFi network optimization, 3G cellular call admission, and the outreach and resources needed.
Contributing Partner: UNT College of Engineering
Robocamp: Encouraging Young Women to Embrace STEM

Robocamp: Encouraging Young Women to Embrace STEM

Date: February 2009
Creator: Akl, Robert G.; Keathly, David & Garlick, Ryan
Description: This presentation discusses Robocamp, a special summer camp that was created by the University of North Texas (UNT) Computer Science and Engineering department. Robocamp successfully promotes engineering among high school women.
Contributing Partner: UNT College of Engineering
WiFi and WCDMA Network Design

WiFi and WCDMA Network Design

Date: April 2005
Creator: Akl, Robert G.
Description: This presentation discusses WiFi access point selection and traffic balancing, multi-cell wideband code division multiple access (WCDMA) with multiple classes, user modeling using 2D Gaussian distribution, and intra-cell and inter-cell interference and capacity.
Contributing Partner: UNT College of Engineering
Cell Design to Maximize Capacity in CDMA Networks

Cell Design to Maximize Capacity in CDMA Networks

Date: April 2002
Creator: Akl, Robert G.
Description: This presentation discusses the code division multiple access (CDMA) inter-cell effects, capacity regions, maximizing network capacity, mobility, a call admission control algorithm, and network performance.
Contributing Partner: UNT College of Engineering