arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.16248cs.CLcs.AI
收藏

基于知识内容选择的主题到文章生成

Topic-to-essay generation with knowledge-based content selection

College of Computer Science, Nankai University(南开大学计算机科学学院)

Jieyong Wang, Chunyao Song, Yihao Wu

AI总结:

针对主题到文章生成任务中文本多样性不足的问题,本文提出融合语言模型语义知识的复制机制模型,并引入改进前缀调优方法,在保持主题一致性的同时将生成多样性提升35%至59%。

摘要:

主题到文章生成任务是一项具有挑战性的自然语言生成任务,旨在基于给定的一组主题词生成具有高语义连贯性的段落级文本。以往的工作侧重于引入外部知识,忽略了生成文本多样性的不足。为了提高生成多样性,我们提出了一种新颖的带有内容选择模块的复制机制模型,该模块将语言模型中丰富的语义知识整合到解码器中。此外,我们引入了改进的前缀调优方法来训练模型,使其能够适应不同的输入复杂度。另外,我们贡献了一个新的用于TEG任务的中文数据集。实验结果表明,与最先进的方法相比,所提出的模型能够在保持高水平主题一致性的同时,将生成文本多样性提高35%至59%。

英文摘要:

The topic-to-essay generation task is a challenging natural language generation task that aims to generate paragraph-level text with high semantic coherence based on a given set of topic words. Previous work has focused on the introduction of external knowledge, ignoring the insufficient generated text diversity. In order to improve the generation diversity, we propose a novel copy mechanism model with a content selection module that integrates rich semantic knowledge from the language model into the decoder. Furthermore, we introduce the improved prefix tuning method to train the model, enabling it to adapt to varying input complexities. In addition, we have contributed a new Chinese dataset for TEG tasks. Experimental results demonstrate that the proposed model can improve the generated text diversity by 35\% to 59\% compared to the state-of-the-art method, while maintaining a high level of topic consistency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑