关键词: 混合式摘要, BERT模型, PEGASUS模型, 层次聚类, 自适应纠错机制, 对比学习框架

Abstract: To address the issues of word redundancy, poor readability in extractive summarization, as well as semantic confusion, logical inconsistency, and exposure bias in abstractive summarization, this paper proposes a two-stage text summarization method based on an improved PEGASUS model and an adaptive error correction mechanism, employing a hybrid summarization technique. In the extraction stage, text vectors are obtained using the BERT model, combined with a Bi-GRU neural network and a graph structure. An improved MMR algorithm is utilized to effectively reduce redundancy in candidate summaries, enhancing summary precision. In the generation stage, the extracted sentences are processed by the PEGASUS model, incorporating hierarchical clustering technology and introducing an adaptive error correction mechanism to solve the out-of-vocabulary (OOV) problem. Additionally, a contrastive learning framework is adopted to significantly mitigate exposure bias. Experimental results demonstrate that our method achieves significant improvements in ROUGE scores on the NLPCC dataset, with average increases of 2.66%, 0.84%, and 1.81% compared to existing hybrid methods. This approach not only improves summary quality but also exhibits superior performance in addressing OOV words and exposure bias.

Key words: Hybrid Summarization, BERT Model, PEGASUS Model, Hierarchical Clustering, Adaptive Error Correction Mechanism, Contrastive Learning Framework