Optimization of the Abstract Text Summarization Model Based on Multi-Task Learning

Automatic text summtarization technology is a crucial component in the field of natural language processing, utilized to address the demands of processing extensive textual data by effectively extracting key information to enhance task efficiency. With the rise of pretrained language models, abstract text summarization has progressively become mainstream, producing fluent srummaries that encapsulate core content. Nonetheless, abstract text summarization unavoidably faces problems of inconsistency with the original text. This paper introduces a sequence tagging task to achieve multi-task learning for abstract text summarization models. In this sequence tagging task, we meticulously designed annotated datasets at both entity and sentence levels based on an analysis of the XSum dataset, aiming to enhance the factual consistency of generated summaries. Experimental results demonstrate that the optimized BART model yields favorable performance in terms of ROUGE and FactCC metrics.