Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.10115 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909290801922048 |
|---|---|
| author | Liu, Ran Liu, Ming Yu, Min Jiang, Jianguo Li, Gang Zhang, Dan Li, Jingyuan Meng, Xiang Huang, Weiqing |
| author_facet | Liu, Ran Liu, Ming Yu, Min Jiang, Jianguo Li, Gang Zhang, Dan Li, Jingyuan Meng, Xiang Huang, Weiqing |
| contents | Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10115 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization Liu, Ran Liu, Ming Yu, Min Jiang, Jianguo Li, Gang Zhang, Dan Li, Jingyuan Meng, Xiang Huang, Weiqing Computation and Language Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER. |
| title | GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.10115 |