Results 1 - 10 of 461

Challenges in Evaluating Summaries of Short Stories

by Anna Kazantseva - In Proceedings of the Workshop on Task-Focused Summarization and Question Answering, at ACL 2006 , 2006
"... This paper presents experiments with the evaluation of automatically produced summaries of literary short stories. The summaries are tailored to a particular purpose of helping a reader decide whether she wants to read the story. The evaluation procedure includes extrinsic and intrinsic measures, as ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
This paper presents experiments with the evaluation of automatically produced summaries of literary short stories. The summaries are tailored to a particular purpose of helping a reader decide whether she wants to read the story. The evaluation procedure includes extrinsic and intrinsic measures

Generating Coherent Extracts of Single Documents Using Latent Semantic Analysis

by Tristan Miller, Tristan Miller , 2003
"... A major problem with automatically-produced summaries in general, and extracts in particular, is that the output text often lacks textual coherence. Our goal is to improve the textual coherence of automatically produced extracts. We developed and implemented an algorithm which builds an initial extr ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
A major problem with automatically-produced summaries in general, and extracts in particular, is that the output text often lacks textual coherence. Our goal is to improve the textual coherence of automatically produced extracts. We developed and implemented an algorithm which builds an initial

Automatic music summarization via similarity analysis

by Matthew Cooper, Jonathan Foote - in Proc. Int. Conf. Music Information Retrieval, 2002
"... We present methods for automatically producing summary excerpts or thumbnails of music. To find the most representative excerpt, we maximize the average segment similarity to the entire work. After window-based audio parameterization, a quantitative similarity measure is calculated between every pai ..."
Abstract - Cited by 67 (3 self) - Add to MetaCart
We present methods for automatically producing summary excerpts or thumbnails of music. To find the most representative excerpt, we maximize the average segment similarity to the entire work. After window-based audio parameterization, a quantitative similarity measure is calculated between every

Task-Driven Software Summarization

by Dave Binkley, Dawn Lawrie, Emily Hill, Janet Burge, Ian Harris, Regina Hebig, Oliver Keszocze, Karl Reed, John Slankas
"... Abstract—There is a growing interest in software summariza-tion and tools for automatically producing summaries. Discus-sions of relevant papers at recent conferences led to the obser-vation that software summarization needs to consider migrating away from “is this a good summary? ” and towards “is ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
Abstract—There is a growing interest in software summariza-tion and tools for automatically producing summaries. Discus-sions of relevant papers at recent conferences led to the obser-vation that software summarization needs to consider migrating away from “is this a good summary? ” and towards “is

Using Latent Semantic Analysis

by Tristan Miller For, Tristan Miller, Tristan Miller , 2003
"... Using Latent Semantic Analysis Tristan Miller Master of Science Graduate Department of Computer Science University of Toronto 2003 A major problem with automatically-produced summaries in general, and extracts in particular, is that the output text often lacks textual coherence. Our goal is to ..."
Abstract - Add to MetaCart
Using Latent Semantic Analysis Tristan Miller Master of Science Graduate Department of Computer Science University of Toronto 2003 A major problem with automatically-produced summaries in general, and extracts in particular, is that the output text often lacks textual coherence. Our goal

Matthew Cooper

by Hillview Avenue Bldg, Matthew Cooper - Proc. IRCAM , 2002
"... We present methods for automatically producing summary excerpts or thumbnails of music. To find the most representative excerpt, we maximize the average segment similarity to the entire work. After window-based audio parameterization, a quantitative similarity measure is calculated between every pai ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
We present methods for automatically producing summary excerpts or thumbnails of music. To find the most representative excerpt, we maximize the average segment similarity to the entire work. After window-based audio parameterization, a quantitative similarity measure is calculated between every

Pronominal anaphora resolution for text summarisation

by Stafford St
"... The assumption of term-based summarisation method is that the importance of a sentence can be determined by the importance of the words it contains. One drawback of these methods is that they usually consider the words in isolation, ignoring relations such as anaphoric links between them. This paper ..."
Abstract - Add to MetaCart
. This paper investigates to what extent the integration of pronominal anaphora resolution into the summarisation process can improve the informativeness of the automatically produced summaries. Evaluation of three anaphora resolution methods plus three baselines on a corpus of journal articles shows

A good space: Lexical predictors in vector space evaluation

by Christian Smith, Henrik Danielsson, Arne Jönsson
"... Vector space models benefit from using an outside corpus to train the model. It is, however, unclear what constitutes a good training corpus. We have investigated the effect on summary quality when using various language resources to train a vector space based extraction summarizer. This is done by ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
by comparing automatically produced summaries to human created gold standard summaries using the ROUGE F-score. Our results show that the genre of the training corpus does not have a significant effect on summary quality. However, evaluating the variance in the F-score between the genres based on lexical

Summary

by Soumendra N. Lahiri, Tapabrata Maiti, Myron Katzoff, Van Parsons , 2006
"... Best linear unbiased prediction is well known for its wide range of applications including small area estimation. While the theory is well established for mixed linear models and under normality of the error and mixing distributions, the literature is sparse for nonlinear mixed models under nonnorma ..."
Abstract - Add to MetaCart
, the proposed methodology automatically produces estimates of the small area parameters and their MSPEs, without requiring explicit analytical expressions for the MSPE.

SUMMARY

by Mr. Simon Ahlberg, Dr. Ulf Söderman, Ms. Åsa Persson, Mr. Magnus Elmqvist
"... Modern conflict situations set new requirements for mission planning and mission rehearsal systems Rapid and appropriate reactions to new situations require updated geographic information and intelligence information about the area of interest. In many cases, this information is inaccurate, outdated ..."
Abstract - Add to MetaCart
resolution laser radar data and imager from airborne platforms. By using modern high-resolution sensors and new automatic sensor data processing methods, we are able to produce data that can be used in C2 systems for mission planning and for building realistic virtual training environments to gain mission
Results 1 - 10 of 461