Number of found records: 80
|
MCKEOWN, Kathleen R.; KLAVANS, Judith L.; HATZIVASSILOGLOU, Vasileios [et al] |
|
Towards Multidocument Summarization by Reformulation: Progress and Prospects |
|
On line (11/05/2005) |
|
By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. We are developing a multidocument summarization system to automatically generate a concise summary by identifying and synthesizing similarities across a set of related documents. Our approach is unique in its integration of machine learning and statistical techniques to identify similar paragraphs, intersection of similar phrases within paragraphs, and language generation to reformulate the wording of the summary. Our evaluation of system components shows that learning over multiple extracted linguistic features is more effective than information retrieval approaches at identifying similar text units for summarization and that it is possible to generate a fluent summary that conveys similarities among documents even when full semantic interpretations of the input text are not available. (AU) |
|
multidocument summarization; reformulation; evaluation |
Assessment |
|
|
|
|
MCLELLAN, Paul; TOMBROS, Anastasios; JOEMON, Jose; et al. |
|
Evaluating Summarisation Technologies: A Task Oriented Approach. |
|
PDF |
|
This paper presents a novel task-oriented approach for the evaluation of automatic text summarisation systems. Evaluation of systems has traditionally been a troublesome area in summarisation research. We propose a scheme that evaluates three existing systems by determining their relative effectiveness in an interactive search task, under conditions that approximate the intended use of the systems. (AU) |
|
evaluation; automatic text summarization |
Assessment |
|
|
|
|
Moens, Marie-Francine |
|
Summarizing court decisions |
|
Information Processing & Management, Nov2007, Vol. 43 Issue 6, p1748-1764 |
|
On line (04/2008) (Only UGR) |
|
In the field of law there is an absolute need for summarizing the texts of court decisions in order to make the content of the cases easily accessible for legal professionals. During the SALOMON and MOSAIC [2] SALOMON (1993-1996) was sponsored by the NFWO grant 80009.93. The MOSAIC project (2001-2003) was sponsored by the K.U.Leuven Onderzoeksfonds grant PDM/00/006-PDM/01/008. 2 projects we investigated the summarization and retrieval of legal cases. This article presents some of the main findings while integrating the research results of experiments on legal document summarization by other research groups. In addition, we propose novel avenues of research for automatic text summarization, which we currently exploit when summarizing court decisions in the ACILA [3] The ACILA project (2006-2010) is financed by the K.U.Leuven Onderzoeksfonds OT/06/03. 3 project. Techniques for automated concept learning and argument recognition are here the most challenging (DB) |
|
Automatic abstracts, legal texts |
Assessment |
|
|
|
|
NEWTON, Paul |
|
HIPPO: Incorporating Hypertext using Fuzzy Components |
|
ACM Hypertext '97 conference, Southampton UK, April 1997 |
|
On line ( 15/06/2004) |
|
Study of the hypertext, its theories and problems, presenting the HIPPO model as well as its techniques and logical components |
|
HIPPO; hypertext; fuzzy components |
Assessment |
|
|
|
|
