Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization

To, Huy Quoc; Nguyen, Kiet Van; Nguyen, Ngan Luu-Thuy; Nguyen, Anh Gia-Tuan

doi:10.48550/arxiv.2108.13741

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…nktd etn id t d nt tit aegid enngntsgitt d a itn d wktnkd wtnhd t iad t d one language. The second t d neiitit aegid enngntsgitt d a itn d ntatnt adntntdikg done language 3 . In general, Arabic text summarization approaches and methodologies are still immature due to ng ad nkgiit at d t d iktd lngltnd ig aegatsd ytnd tign it d lngltnd itii d meaning depends on the nt itii d nnt -tgitnigid a gntgitt d nt t ntd tnd gl t ntdte tgnntitn dg diktdtagiegitt dprocess of Arabic summarization systems 4,5 .…”

Section: Introductionmentioning

confidence: 99%

A Novel Gravity ‎Optimization Algorithm for Extractive Arabic Text Summarization

2023

View full text Add to dashboard Cite

An automatic text summarization system mimics how humans summarize by picking the most ‎significant sentences in a source text. However, the complexities of the Arabic language have become ‎challenging to obtain information quickly and effectively. The main disadvantage of the ‎traditional approaches is that they are strictly constrained (especially for the Arabic language) by the ‎accuracy of sentence feature ‎functions, weighting schemes, ‎and similarity calculations. On the other hand, the meta-heuristic search approaches have a feature that tolerates imprecision, gets ‎prohibited results, and is not strictly bound by the above ‎restrictions. This ‎paper used the Gravitational Optimization Algorithm (GOA), a powerful metaheuristic ‎approach ‎based on the law of ‎gravity, to address the challenge of extractive summarizing Arabic texts. The objective function of the GOA algorithm is derived based on sentence significance, such as its length, ‎similarity degree, position, statistical term frequency, and named entity ownership. Essex Arabic ‎Summaries Corpus (EASC) was used to evaluate the proposed method and measured by the Recall-Oriented Understudy for Gisting Evaluation (ROUGE). The proposed approach achieved 68.04% Recall, ‎‎58.49% Precision, and 60.05% F1-measure using ROUGE-1, higher than standard summarizers and metaheuristic approaches

show abstract

Section: Introductionmentioning

confidence: 99%