BERT-VBD: Vietnamese Multi-Document Summarization Framework

TL;DR

This paper introduces a Vietnamese multi-document summarization framework that combines extractive and abstractive methods using BERT and VBD-LLaMA2-7B-50b, achieving superior ROUGE scores on the VN-MDS dataset.

Contribution

It proposes a novel two-component pipeline integrating modified BERT for extraction and VBD-LLaMA2 for abstraction tailored to Vietnamese MDS.

Findings

Achieved ROUGE-2 score of 39.6% on VN-MDS dataset

Outperformed existing state-of-the-art baselines

Demonstrated effectiveness of combined extractive-abstractive approach

Abstract

In tackling the challenge of Multi-Document Summarization (MDS), numerous methods have been proposed, spanning both extractive and abstractive summarization techniques. However, each approach has its own limitations, making it less effective to rely solely on either one. An emerging and promising strategy involves a synergistic fusion of extractive and abstractive summarization methods. Despite the plethora of studies in this domain, research on the combined methodology remains scarce, particularly in the context of Vietnamese language processing. This paper presents a novel Vietnamese MDS framework leveraging a two-component pipeline architecture that integrates extractive and abstractive techniques. The first component employs an extractive approach to identify key sentences within each document. This is achieved by a modification of the pre-trained BERT network, which derives semantically meaningful phrase embeddings using siamese and triplet network structures. The second component utilizes the VBD-LLaMA2-7B-50b model for abstractive summarization, ultimately generating the final summary document. Our proposed framework demonstrates a positive performance, attaining ROUGE-2 scores of 39.6% on the VN-MDS dataset and outperforming the state-of-the-art baselines.