A systematic evaluation of both extractive methods based on sentence ranking and an abstractive approach using a fine-tuned mT5-base model for Azerbaijani text summarization yields strong results that highlight the benefits of task specific fine-tuning for abstractive summarization, while also demonstrating the competitiveness of extractive baselines.
Abstract
This article investigates extractive and abstractive text summarization for the Azerbaijani language, a low-resource and underrepresented language in natural language processing. While the underlying modeling approaches are well established, their application to Azerbaijani summarization remains largely unexplored due to the scarcity of large-scale datasets and prior empirical studies. To address this gap, we conduct a systematic evaluation of both extractive methods based on sentence ranking and an abstractive approach using a fine-tuned mT5-base model. Our experiments are carried out on a large-scale dataset comprising over 115,000 Azerbaijani news articles paired with human-written summaries. The models are evaluated using standard automatic metrics, including Recall-Oriented Understudy for Gisting Evaluation (ROUGE), Bilingual Evaluation Understudy (BLEU), and Metric for Evaluation of Translation with Explicit ORdering (METEOR), yielding strong results that highlight the benefits of task specific fine-tuning for abstractive summarization, while also demonstrating the competitiveness of extractive baselines. In addition, we analyze the impact of long input sequences and discuss architectural and dataset-related limitations affecting performance. Overall, this study provides a comprehensive empirical baseline for Azerbaijani text summarization and serves as a reference point for future research in low-resource summarization and related Azerbaijani Natural Language Processing (NLP) applications.
The results show that BART achieves the best performance with an ROUGE-2 F1-score of 0.40664, while T5 demonstrates superior grammatical acceptability, achieving 93.36%, but BART achieves a very near performance to T5.
Emad Nabil· Islamic University Journal o...· 0 citations
The proposed framework using Bidirectional Long Short-Term Memory with a hypergraph and a dominating set mechanism proves to be an efficient approach to automatic summarization and has the potential to be applied in journalism, healthcare, legal analysis, and digital content management.
Pradeepa Sampath, S. Subashini, V. Shanmuganathan et al.· Artificial Intelligence and...· 0 citations
The increasing number of scientific publications has made literature screening more time-consuming, particularly for researchers who need to identify the main contribution of an article before reading the full text. This study develops an extractive summarization model for Indonesian scientific articles using a BERT-based transfer learning approach. The proposed method represents each sentence with contextual embeddings and selects relevant sentences based on their similarity to the document representation, while applying a redundancy threshold to reduce redundancy. A curated corpus of Indonesian research articles was used for model development and evaluation. The generated summaries were evaluated using ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-Lsum, with the article abstract used as the reference summary. The experimental results show that the proposed model achieved a ROUGE-1 score of approximately 33%, indicating it retained important keywords and central information from the source documents. However, the lower ROUGE-2 score suggests that the model still has limitations in preserving phrase-level continuity and sentence coherence. Qualitative analysis also shows that the model can capture the main ideas of scientific articles, although some methodological details and contextual information are occasionally omitted. These findings indicate that BERT-based extractive summarization can support preliminary literature screening, but further improvement is needed through stronger baseline comparison, human evaluation, and redundancy-aware optimization.
Made Hanindia Prami Swari, Puji Lestari Tarigan, Gusti Eka Yuliastuti et al.· JOIV: International Journal...· 0 citations
Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to create accurate summaries. Active learning mitigates this issue by selecting only the most informative instances for annotation, allowing models to achieve competitive results with significantly fewer labels. However, the application of active learning to summarization remains under-explored, and existing studies often suffer from instability and significant computational bottlenecks. To overcome these challenges, we propose LOBSTER (LOss-BaSed acTivE leaRning), a novel active learning framework designed specifically for abstractive summarization. LOBSTER improves performance by prioritizing unlabeled instances semantically similar to the model's current high-loss training examples, enabling the model to explicitly correct its specific weaknesses. Our empirical evaluation across three benchmark datasets and two summarization backbone models demonstrates that LOBSTER consistently matches or outperforms current state-of-the-art approaches while achieving a query selection speedup of up to 665x.
M. Ioannou, Tatiana Passali, George Michalopoulos et al.· 0 citations
The proposed MLOA-MA-ASeqNet architecture, a Multi-scale Attention and Adaptive Sequence-to-Sequence Network whose hierarchical encoder operates simultaneously at word, phrase and sentence level granularity, achieves the highest average score across fluency, adequacy, coherence and readability.
V. M, Kunal Chakma, Anupam Jamatia et al.· ACM Transactions on Asian an...· 0 citations
AI-based text summarization plays a critical role in managing the rapidly increasing volume of textual information by enabling efficient information retrieval and concise knowledge representation. Conventional summarization approaches often rely on heuristic rules and surface-level features, limiting their ability to capture contextual relevance and semantic coherence in long documents. To overcome these limitations, this study develops a deep learning–based extractive text summarization framework using a hybrid Bidirectional Encoder Representations from Transformers (BERT) combined with Bidirectional Long Short-Term Memory (BiLSTM) architecture. The model leverages BERT’s bidirectional transformer encoder to generate rich contextual sentence embeddings and employs a BiLSTM network to model inter-sentence dependencies and document-level structure, enabling effective identification of summary-worthy sentences while preserving original semantic content. The framework is evaluated using the BBC News Summary dataset, which contains professionally written news articles and corresponding human reference summaries. Performance is assessed through sentence-level classification metrics and ROUGE-based evaluation. Experimental results demonstrate strong effectiveness, achieving an overall accuracy of 98.5%, with balanced precision (98.7%), recall (98.2%), and F1-score (98.45%), indicating reliable sentence importance classification. In addition, the model attains competitive ROUGE ((Recall-Oriented Understudy for Gisting Evaluation) scores (ROUGE-1 = 0.56, ROUGE-2 = 0.33, and ROUGE-L = 0.52), confirming substantial overlap with human summaries. These results highlight the robustness, generalization capability, and practical applicability of the suggested BERT–BiLSTM structure for automatic text summarization and knowledge representation.
Dr. RakeshKumar ER, S. Ramachandran, Ayushi Khandal et al.· 2026 7th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
