Arabic Single-Document Text Summarization Using Particle Swarm Optimization Algorithm

Al-Abdallah, Raed Z.; Al-Taani, Ahmad T.

doi:10.1016/j.procs.2017.10.091

Cited by 59 publications

(36 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We chose five systems using the same data set (EASC) for experimentations. The chosen systems are Gen‐Summ and LSA‐Summ (Elhaj et al, 2010), LCEAS Al‐Khwaldeh & Samawi, , PSO Al‐Abdallah & Al‐Taani, , and mRMR Oufaida et al, . The comparison is made against the ROUGE‐2 metric and using recall, precision, and F ‐measure.…”

Section: Resultsmentioning

confidence: 99%

“…Path browsing is based on the maximization of the f value of each node n. g is the sum of all edges' values (cosine scores) of the path that leads from the initial node until the node n. h is calculated by adding two scores, the GC score and the position score (Equation 11). The position of a segment in a text was always a very good parameter in the selection of the most relevant segments Douzidia & Lapalme, 2004;Al-Abdallah & Al-Taani, 2017. We give more priority to the first and with a little less priority to the second segment in the text.…”

Section: A* Reductionmentioning

confidence: 99%

“…According to a predefined threshold, the final summary includes only sentences that are not entailed by others. More recently, Al‐Abdallah and Al‐Taani () presented an updated version of that proposed by Al‐Taani and El‐Omour (). As in Douzidia and Lapalme (), an informative statistical score is associated to each sentence.…”

Section: Background and Related Workmentioning

confidence: 99%

“…h is calculated by adding two scores, the GC score and the position score (Equation 11). The position of a segment in a text was always a very good parameter in the selection of the most relevant segments Douzidia & Lapalme, ; Al‐Abdallah & Al‐Taani, . We give more priority to the first and with a little less priority to the second segment in the text.

h ((), n) = italicGC ((), n) + \frac{1}{italicposition ((), n)}

position ( n ) is the position of the segment n in the text.…”

Section: Proposed Approachmentioning

confidence: 99%

“…As a solution to these problems, we propose to apply a subtopic selection process (see Section 3.6). Graph‐based approaches (see Al‐Abdallah & Al‐Taani, ; Al‐Taani & El‐Omour, ) constitute a good alternative and take advantage of the powerful techniques and algorithms used in graph theory to select the most relevant passages in a text. The results can be much better if they take semantic relations into account.…”

Section: Background and Related Workmentioning

confidence: 99%

See 4 more Smart Citations

ArAsummarizer: An Arabic text summarization system based on subtopic segmentation and using an A algorithm for reduction

2020

View full text Add to dashboard Cite

Automatic text summarization is a field situated at the intersection of natural language processing and information retrieval. Its main objective is to automatically produce a condensed representative form of documents. This paper presents ArA*summarizer, an automatic system for Arabic single document summarization. The system is based on an unsupervised hybrid approach that combines statistical, cluster‐based, and graph‐based techniques. The main idea is to divide text into subtopics then select the most relevant sentences in the most relevant subtopics. The selection process is done by an A* algorithm executed on a graph representing the different lexical–semantic relationships between sentences. Experimentation is conducted on Essex Arabic summaries corpus and using recall‐oriented understudy for gisting evaluation, automatic summarization engineering, merged model graphs, and n‐gram graph powered evaluation via regression evaluation metrics. The evaluation results showed the good performance of our system compared with existing works.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: A* Reductionmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

h ((), n) = italicGC ((), n) + \frac{1}{italicposition ((), n)}

position ( n ) is the position of the segment n in the text.…”

Section: Proposed Approachmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

See 3 more Smart Citations

ArAsummarizer: An Arabic text summarization system based on subtopic segmentation and using an A algorithm for reduction

2020

View full text Add to dashboard Cite

show abstract

Abstractive text summarization using deep learning with a new Turkish summarization benchmark dataset

Ertam

Aydın

2021

Concurrency and Computation

View full text Add to dashboard Cite

Exponential increase in the amount of textual data made available on the Internet results in new challenges in terms of accessing information accurately and quickly.Text summarization can be defined as reducing the dimensions of the expressions to be summarized without spoiling the meaning. Summarization can be performed as extractive and abstractive or using both together. In this study, we focus on abstractive summarization which can produce more human-like summarization results. For the study we created a Turkish news summarization benchmark dataset from various news agency web portals by crawling the news title, short news, news content, and keywords for the last 5 years. The dataset is made publicly available for researchers.The deep learning network training was carried out by using the news headlines and short news contents from the prepared dataset and then the network was expected to create the news headline as the short news summary. To evaluate the performance of this study, Rouge-1, Rouge-2, and Rouge-L were compared using precision, sensitivity and F1 measure scores. Performance values for the study were presented for each sentence as well as by averaging the results for 50 randomly selected sentences.The F1 Measure values are 0.4317, 0.2194, and 0.4334 for Rouge-1, Rouge-2, and Rouge-L respectively. Performance results show that the approach is promising for Turkish text summarization studies and the prepared dataset will add value to the literature.

show abstract

Concept Identification from Single-Documents

Ochoa-Hernández

Barceló-Valenzuela

Sanchez-Smitz

et al. 2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

Arabic Single-Document Text Summarization Using Particle Swarm Optimization Algorithm

Cited by 59 publications

References 14 publications

ArAsummarizer: An Arabic text summarization system based on subtopic segmentation and using an A algorithm for reduction

ArAsummarizer: An Arabic text summarization system based on subtopic segmentation and using an A algorithm for reduction

Abstractive text summarization using deep learning with a new Turkish summarization benchmark dataset

Concept Identification from Single-Documents

Contact Info

Product

Resources

About

Arabic Single-Document Text Summarization Using Particle Swarm Optimization Algorithm

Cited by 59 publications

References 14 publications

ArA*summarizer: An Arabic text summarization system based on subtopic segmentation and using an A* algorithm for reduction

ArA*summarizer: An Arabic text summarization system based on subtopic segmentation and using an A* algorithm for reduction

Abstractive text summarization using deep learning with a new Turkish summarization benchmark dataset

Concept Identification from Single-Documents

Contact Info

Product

Resources

About

ArAsummarizer: An Arabic text summarization system based on subtopic segmentation and using an A algorithm for reduction

ArAsummarizer: An Arabic text summarization system based on subtopic segmentation and using an A algorithm for reduction