ENHANCED TEXT SUMMARIZATION WITH GLOBAL AND LOCAL CONTEXT
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901204977582080 |
|---|---|
| author | Leela Prasad |
| author_facet | Leela Prasad |
| contents | <p>In recent years, encoder–decoder architectures have become fundamental to abstractive text summarization, <br>enabling models to process variable-length documents efficiently. Among these, transformer-based systems <br>leverage attention mechanisms that connect distant parts of a text, strengthening their contextual comprehension. <br>However, such global context often overlooks hierarchical detail, requiring additional modelling strategies to <br>capture both broader and finer document structures. <br>This study introduces an enhanced summarization framework that integrates prior knowledge to balance global <br>and local understanding. The proposed design employs two complementary encoding mechanisms: global <br>information-aware encoding, which generates a holistic representation of the document to guide summary <br>generation, and local information-aware encoding, which applies convolutional operations to capture fine-grained <br>textual features. Evaluations on the LCSTS and CSL datasets demonstrate improved ROUGE scores compared to <br>baseline and leading benchmark systems, confirming that integrating multi-level representations enhances <br>summary accuracy and informativeness.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17559075 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ENHANCED TEXT SUMMARIZATION WITH GLOBAL AND LOCAL CONTEXT Leela Prasad Abstractive Summarization, Encoder-Decoder Architecture, Transformer, Global and Local Encoding, Natural Language Processing, Machine Learning <p>In recent years, encoder–decoder architectures have become fundamental to abstractive text summarization, <br>enabling models to process variable-length documents efficiently. Among these, transformer-based systems <br>leverage attention mechanisms that connect distant parts of a text, strengthening their contextual comprehension. <br>However, such global context often overlooks hierarchical detail, requiring additional modelling strategies to <br>capture both broader and finer document structures. <br>This study introduces an enhanced summarization framework that integrates prior knowledge to balance global <br>and local understanding. The proposed design employs two complementary encoding mechanisms: global <br>information-aware encoding, which generates a holistic representation of the document to guide summary <br>generation, and local information-aware encoding, which applies convolutional operations to capture fine-grained <br>textual features. Evaluations on the LCSTS and CSL datasets demonstrate improved ROUGE scores compared to <br>baseline and leading benchmark systems, confirming that integrating multi-level representations enhances <br>summary accuracy and informativeness.</p> |
| title | ENHANCED TEXT SUMMARIZATION WITH GLOBAL AND LOCAL CONTEXT |
| topic | Abstractive Summarization, Encoder-Decoder Architecture, Transformer, Global and Local Encoding, Natural Language Processing, Machine Learning |
| url | https://doi.org/10.5281/zenodo.17559075 |