About: Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion
Creator	Brockett, Chris Nenkova, Ani Suzuki, Hisami Vanderwende, Lucy
Source	PMC
abstract	In recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed to accomplish this task comprises four main components: a generic extractive summarization system, a topic-focusing component, sentence simplification, and lexical expansion of topic words. This paper details each of these components, together with experiments designed to quantify their individual contributions. We include an analysis of our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Additionally, we include an analysis of our results on the DUC2006 task according to human evaluation metrics. In the human evaluation of system summaries compared to human summaries, i.e., the Pyramid method, our system ranked first out of 22 systems in terms of overall mean Pyramid score; and in the human evaluation of summary responsiveness to the topic, our system ranked third out of 35 systems.
has issue date	2007-04-19(xsd:dateTime)
bibo:doi	10.1016/j.ipm.2007.01.023
has license	no-cc
schema:url	https://doi.org/10.1016/j.ipm.2007.01.023
resource representing a document's title	Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion
has PubMed Central identifier	PMC7115785
schema:publication	Inf Process Manag
resource representing a document's body	covid:PMC7115785#body_text
is schema:about of	named entity 'summarization' named entity 'probability' named entity 'NIST metrics' named entity 'probability' named entity 'Encarta' named entity 'probability' named entity 'NIST' named entity 'NIST' named entity 'appositives' named entity 'parser' named entity 'NIST' named entity 'bitext' named entity 'Support Vector Machine' named entity 'linear combination' named entity 'Tanzania' named entity 'bigram' named entity 'probability' named entity 'multi-document summarization' named entity 'parser' named entity 'WordNet' named entity '0.9' named entity 'similarity measure' named entity 'probability' named entity 'unigram' named entity 'NIST' named entity 'parser' named entity 'NIST' named entity 'stopwords' named entity 'named entities' named entity 'gerundive' named entity 'probability' named entity 'probability' named entity 'bigram' named entity 'American Heritage Dictionary' named entity 'parser' named entity 'parser' named entity 'NIST' named entity 'probability' named entity 'NIST' named entity 'multi-document summarization' named entity 'childhood obesity' named entity 'complementizer' named entity 'algorithm' named entity 'parse tree' named entity 'bigrams' named entity 'bootstrapping methods' named entity 'parser' named entity 'banana' named entity 'parser' named entity 'United States' named entity 'parse tree' named entity 'probability' named entity 'unigram' named entity 'multi-document summarization' named entity 'correlation' named entity 'unigram' named entity 'appositive' named entity 'semantic equivalence' named entity 'automatic summarization' named entity 'NIST' named entity 'NIST' named entity 'Pyramid method' named entity 'query expansion' named entity 'NIST' named entity 'parse tree' named entity 'multi-document summarization' named entity 'Word Association' named entity 'restrictive relative clause' named entity 'bigram' named entity 'MDT' named entity 'unigram' named entity 'adverb' named entity 'maximum likelihood' named entity 'bigram' named entity 'National Institute of Standards and Technology' named entity 'Encarta' named entity 'statistically significant' named entity 'bigram' named entity 'probability' named entity 'World Wide Web' named entity 'probability'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software