Performance analysis of Modified Shuffled Frog leaping Algorithm for Multi-document Summarization Problem

Rautray, Rasmita; Dash, Rasmita; Dash, Rajashree

doi:10.31449/inf.v43i3.2310

Cited by 1 publication

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated the proposed method from various perspectives, including automatic accuracy evaluation of the results, human preference evaluation, the effect of local feature FIGURE 6: Visualization of the summarization process for a CNN article about "California Drought" 7 . The left side is the original text, while the right one is the summarization process (three iterations).…”

Section: Resultsmentioning

confidence: 99%

“…Extractive summarization can be either unsupervised or supervised. In unsupervised approaches, the goal is to find representative sentences while in supervised methods, the problem is considered as a binary classification task where classes defined as being/not being included in the summary [6,7]. In this paper, we present a novel intelligent approach for summarization, called ExDoS, which benefits from using both supervised and unsupervised algorithms simultaneously and in an interpretable manner.…”

Section: Introductionmentioning

confidence: 99%

“…We run ROUGE 1.5.5: http://www.berouge.com/Pages/defailt.aspx with parameters -n 2 -m -u -c 95 -r 1000 -f A -p 0.5 -t 07 http://www.cnn.com/2015/04/03/us/california-drought/…”

mentioning

confidence: 99%

See 2 more Smart Citations

Extractive Document Summarization Based on Dynamic Feature Space Mapping

et al. 2020

View full text Add to dashboard Cite

The exponential growth of the Web documents has constituted the need for automatic document summarization. In this context, extractive document summarization, i.e., that task of extracting the most relevant information, removing redundancy and presenting the remained data in a coherent and cohesive structure, is a challenging task. In this paper, we propose a novel intelligent approach, namely ExDoS, that harvests benefits of both supervised and unsupervised algorithms simultaneously. To the best of our knowledge, ExDoS is the first approach to combine both supervised and unsupervised algorithms in a single framework and an interpretable manner for document summarization purpose. ExDoS iteratively minimizes the error rate of the classifier in each cluster with the help of dynamic local feature weighting. Moreover, this approach specifies the contribution of features to discriminate each class, which is a challenging issue in the summarization task. Therefore, in addition to summarizing text, ExDoS is also able to measure the importance of each feature in the summarization process. We evaluate our model both automatically (in terms of ROUGE factor) and empirically (human analysis) on the benchmark datasets: the DUC2002 and CNN/DailyMail. Results show that our model obtains higher ROUGE scores comparing to most state-of-the-art models. The human evaluation also demonstrates that our model is capable of generating informative and readable summaries.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%