Summary of Bert-vbd: Vietnamese Multi-document Summarization Framework, by Tuan-cuong Vuong et al.
BERT-VBD: Vietnamese Multi-Document Summarization Framework
by Tuan-Cuong Vuong, Trang Mai Xuan, Thien Van Luong
First submitted to arxiv on: 18 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel Multi-Document Summarization (MDS) framework for Vietnamese language processing that combines extractive and abstractive summarization techniques. The proposed two-component pipeline architecture first employs an extractive approach to identify key sentences using a modified pre-trained BERT network, and then utilizes the VBD-LLaMA2-7B-50b model for abstractive summarization. The framework demonstrates positive performance on the VN-MDS dataset with a ROUGE-2 score of 39.6%, outperforming state-of-the-art baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes a new way to summarize many documents together, using both extractive and abstractive methods. It’s especially good for Vietnamese language processing. The method is like two steps: first, it finds the most important sentences in each document using a special computer network called BERT. Then, it uses another model called VBD-LLaMA2-7B-50b to create a summary of all the documents together. This new way works well and does better than other methods. |
Keywords
» Artificial intelligence » Bert » Rouge » Summarization
