Publications
Preprint · arXiv · July 5, 2023
Named Entity Inclusion in Abstractive Text Summarization
Berezin, Sergey, Tatiana Viktorovna Batura
Abstract
We address the named entity omission - the drawback of many current abstractive text summarizers. We suggest a custom pretraining objective to enhance the model's attention on the named entities in a text. At first, the named entity recognition model RoBERTa is trained to determine named entities in the text. After that, this model is used to mask named entities in the text and the BART model is trained to reconstruct them. Next, the BART model is fine-tuned on the summarization task. Our experiments showed that this pretraining approach improves named entity inclusion precision and recall metrics.
Topic ModelingAdvanced Text Analysis TechniquesNatural Language Processing Techniquesabstractive summarizationnamed entity recognitionRoBERTa
More by Tatiana Batura
- Entity Linking of Scientific Terms in Specialized Domains and Low-Resource SettingsApplied Sciences · 2026
- SciMDIX: A dataset for aspect extraction from multi-domain scientific documents in Kazakh and RussianProcedia Computer Science · 2026 · Citations: 1
- From text to knowledge: Entity linking of scientific terms to WikipediaBulletin of the Novosibirsk Computing Center Series Computer Science · 2025
- Kazakh Text Classification using Deep Learning ApproachesInternational Conference on Computer Science and Engineering · 2025 · Citations: 1
