北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2025, Vol. 48 ›› Issue (1): 14-20.

• 论文 • 上一篇    下一篇

基于多语义表示的两阶段交互式论点对抽取方法

于宁,石宇,刘建毅   

  1. 北京邮电大学
  • 收稿日期:2023-12-28 修回日期:2024-03-17 出版日期:2025-02-26 发布日期:2025-02-25
  • 通讯作者: 刘建毅 E-mail:liujy@bupt.edu.cn
  • 基金资助:
    国家自然科学基金;北京邮电大学中央高校基本科研业务费项目

Two-Stage Approach Based on Multi-Semantic Representation for Interactive Argument Pair Extraction

YU Ning, SHI Yu, LIU Jianyi   

  • Received:2023-12-28 Revised:2024-03-17 Online:2025-02-26 Published:2025-02-25

摘要: 交互式论点对抽取的目的是从两篇相关的论辩性文本中抽取出多对具有交互性的论点对。现有的方法将该任务分解为论点挖掘和论点对抽取两个子任务,并对子任务进行联合建模,进行多任务学习。然而,在这类方法中,两个不同的子任务共享相同的句子语义表示,导致单个子任务获取的信息有所偏差。因此,提出了一种基于多语义表示的两阶段交互式论点对抽取方法。首先,论点挖掘阶段利用预训练语言模型和双向的编码器来捕获单篇文本的语义信息,从而实现对论点的识别;然后,论点对抽取阶段直接将两个论点建模为文本对进行语义表示,并利用大语言模型对冗长的论点内容进行关键信息抽取,生成新样本,引入关键语义信息,最终完成交互式论点对的识别。在两个基准数据集上进行了实验,结果表明,所提方法的性能优于基线方法,证明了所提方法的有效性。

关键词: 多语义表示, 大语言模型, 交互式论点对抽取

Abstract: Interactive argument pair extraction aims to identify multiple argument pairs from two related argumentative texts. The task is decomposed into two subtasks by current methods: argument mining and argument pair extraction, which are then jointly modeled for multi-task learning. However, the same sentence semantic representations are shared by these methods, which may lead to information bias within each subtask. Therefore, a two-stage interactive argument pair extraction method based on multi-semantic representation is proposed. First, a pre-trained language model and a bidirectional encoder are utilized in the argument mining stage to capture the semantic information of a single text for argument identification. Then, the two arguments are directly modeled as a text pair for semantic representation in the argument pair extraction stage. A large language model is used to extract key information from lengthy argument content, new samples are generated, key semantic information is introduced, and ultimately the identification of interactive argument pairs is completed. Experiments are conducted on two benchmark datasets, the results show that the proposed method outperformed the baseline method, demonstrating its effectiveness.

Key words: multi-semantic representation, large language model, interactive argument pair extraction

中图分类号: