Difference between revisions of "Exploring Simultaneous Keyword and Key Sentence Extraction: Improve Graph-Based Ranking Using Wikipedia"
(Exploring Simultaneous Keyword and Key Sentence Extraction: Improve Graph-Based Ranking Using Wikipedia - basic info) |
(+ wikilinks) |
||
| Line 1: | Line 1: | ||
| − | '''Exploring Simultaneous Keyword and Key Sentence Extraction: Improve Graph-Based Ranking Using Wikipedia''' - scientific work related to Wikipedia quality published in 2012, written by Xun Wang, Lei Wang, Jiwei Li and Sujian Li. | + | '''Exploring Simultaneous Keyword and Key Sentence Extraction: Improve Graph-Based Ranking Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2012, written by [[Xun Wang]], [[Lei Wang]], [[Jiwei Li]] and [[Sujian Li]]. |
== Overview == | == Overview == | ||
| − | Summarization and Keyword Selection are two important tasks in NLP community. Although both aim to summarize the source articles, they are usually treated separately by using sentences or words. In this paper, authors propose a two-level graph based ranking algorithm to generate summarization and extract keywords at the same time. Previous works have reached a consensus that important sentence is composed by important keywords. In this paper, authors further study the mutual impact between them through context analysis. Authors use Wikipedia to build a two-level concept-based graph, instead of traditional term-based graph, to express their homogenous relationship and heterogeneous relationship. Authors run PageRank and HITS rank on the graph to adjust both homogenous and heterogeneous relationships. A more reasonable relatedness value will be got for key sentence selection and keyword selection. Authors evaluate algorithm on TAC 2011 data set. Traditional term-based approach achieves a score of 0.255 in ROUGE-1 and a score of 0.037 and ROUGE-2 and approach can improve them to 0.323 and 0.048 separately. | + | Summarization and Keyword Selection are two important tasks in NLP community. Although both aim to summarize the source articles, they are usually treated separately by using sentences or words. In this paper, authors propose a two-level graph based ranking algorithm to generate summarization and extract keywords at the same time. Previous works have reached a consensus that important sentence is composed by important keywords. In this paper, authors further study the mutual impact between them through context analysis. Authors use [[Wikipedia]] to build a two-level concept-based graph, instead of traditional term-based graph, to express their homogenous relationship and heterogeneous relationship. Authors run PageRank and HITS rank on the graph to adjust both homogenous and heterogeneous relationships. A more reasonable [[relatedness]] value will be got for key sentence selection and keyword selection. Authors evaluate algorithm on TAC 2011 data set. Traditional term-based approach achieves a score of 0.255 in ROUGE-1 and a score of 0.037 and ROUGE-2 and approach can improve them to 0.323 and 0.048 separately. |
Revision as of 20:54, 30 September 2019
Exploring Simultaneous Keyword and Key Sentence Extraction: Improve Graph-Based Ranking Using Wikipedia - scientific work related to Wikipedia quality published in 2012, written by Xun Wang, Lei Wang, Jiwei Li and Sujian Li.
Overview
Summarization and Keyword Selection are two important tasks in NLP community. Although both aim to summarize the source articles, they are usually treated separately by using sentences or words. In this paper, authors propose a two-level graph based ranking algorithm to generate summarization and extract keywords at the same time. Previous works have reached a consensus that important sentence is composed by important keywords. In this paper, authors further study the mutual impact between them through context analysis. Authors use Wikipedia to build a two-level concept-based graph, instead of traditional term-based graph, to express their homogenous relationship and heterogeneous relationship. Authors run PageRank and HITS rank on the graph to adjust both homogenous and heterogeneous relationships. A more reasonable relatedness value will be got for key sentence selection and keyword selection. Authors evaluate algorithm on TAC 2011 data set. Traditional term-based approach achieves a score of 0.255 in ROUGE-1 and a score of 0.037 and ROUGE-2 and approach can improve them to 0.323 and 0.048 separately.
