AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization

Eddine, Moussa Kamal; Tomeh, Nadi; Habash, Nizar; Roux, Joseph Le; Vazirgiannis, Michalis

doi:10.48550/arxiv.2203.10945

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall, precision, and F-measure all improved to 72.94, 68.75, and 67.99. In (Eddine et al 2022) AraBart was the first sequence-to-sequence pre-trained Arabic model. Their model was tested on abstractive summarization tasks at various abstraction levels.…”

Section: Literature Reviewmentioning

confidence: 99%

Hybrid Arabic text summarization Approach based on Seq-to-seq and Transformer

Elsaid

Mohammed

Fattouh

et al. 2023

Preprint

View full text Add to dashboard Cite

Text summarization is essential in natural language processing as the data volume increases quickly. Therefore, the user needs to summarize that data into a meaningful text in a short time. There are two common methods of text summarization: extractive and abstractive. There are many efforts to summarize Latin texts. However, summarizing Arabic texts is challenging for many reasons, including the language’s complexity, structure, and morphology. Also, there is a need for benchmark data sources and a gold standard Arabic evaluation metrics summary. Thus, the contribution of this paper is multi-fold: First, the paper proposes a hybrid approach consisting of a Modified Sequence-To-Sequence (MSTS) model and a transformer-based model. The seq-to-seq-based model is modified by adding multi-layer encoders and a one-layer decoder to its structure. The output of the MSTS model is the extractive summarization. To generate the abstractive summarization, the extractive summarization is manipulated by a transformer-based model. Second, it introduces a new Arabic benchmark dataset, called the HASD, which includes 43k articles with their extractive and abstractive summaries. Third, this work modifies the well-known extractive EASC benchmarks by adding to each text its abstractive summarization. Finally, this paper proposes a new measure called the Arabic-rouge measure for the abstractive summary depending on structure and similarity between words. The proposed method is tested using the proposed HASD and Modified EASC benchmarks and evaluated using Rouge, Bleu, and Arabic Rouge. The experimental results show satisfactory results compared to state-of-the-art methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Hybrid Arabic text summarization Approach based on Seq-to-seq and Transformer

Elsaid

Mohammed

Fattouh

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…BERTScore [8] is yet another metric that computes a similarity score between the system sentence and the reference sentence based on pre-trained BERT contextual embeddings. AraBART model [9] evaluated using BERTScore.…”

Section: B Evaluating Summariesmentioning

confidence: 99%

“…It has been used to evaluate various abstractive summarization models [3,5,9,[11][12][13], covering different techniques such as deep learning and graph-based models [14,15].…”

Section: B Evaluating Summariesmentioning

confidence: 99%

LEMMA-ROUGE: An Evaluation Metric for Arabic Abstractive Text Summarization

Al-Numai

Azmi

2023

ijcs

View full text Add to dashboard Cite

High morphological languages are characterized by complex inflections and derivations, which can present challenges for natural language processing tasks such as summarization. Abstractive text summarization aims to generate a summary by understanding the meaning of the text, rather than solely relying on the words used in the original source. However, few works address the generation of abstractive summaries due to its complexity. One of the challenges is the absence of a reliable metric to evaluate the performance of abstractive summaries. This paper proposes a lemma-based ROUGE metric and investigates the effectiveness of normalization forms in the similarity matching of the ROUGE metric for evaluating abstractive text summarization systems. We use Arabic as a case study and compare results involving different forms of the word: as is, stem-based, and lemma-based. The results show that the lemma-based form achieves higher ROUGE scores than the other forms. The findings emphasize the impact of morphological complexity on the performance of abstractive text summarization systems.

show abstract

AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization

Cited by 2 publications

References 0 publications

Hybrid Arabic text summarization Approach based on Seq-to-seq and Transformer

Hybrid Arabic text summarization Approach based on Seq-to-seq and Transformer

LEMMA-ROUGE: An Evaluation Metric for Arabic Abstractive Text Summarization

Contact Info

Product

Resources

About