Research on Contrastive Viewpoint Summarization for Opinionated Texts
2013 ◽
Vol 14
(03)
◽
pp. 1360003
◽
This paper presents a two-stage approach for multi-topic contrastive viewpoint summarization on opinionated texts. In the first stage, we model the opinionated texts with TAM and get the topic and aspect attribute of each sentence. In the second stage, we successively use the basic LexRank, Comparative LexRank, Topic-sensitive tf*idf LexRank, Topic-sensitive tf*idf & Comparative LexRank, and Biased & Comparative LexRank to evaluate the centrality of each sentence, based on which the summary is finally generated. Experimental results show that the best summary comes from the proposed Topic-sensitive tf*idf LexRank and Topic-sensitive tf*idf & Comparative LexRank.
2020 ◽
2020 ◽
1991 ◽
Vol 113
(4)
◽
pp. 709-713
◽
2021 ◽
Keyword(s):
2019 ◽
Vol 10
(1)
◽
pp. 69-82
◽
Keyword(s):