Scholarlink

<p>Implicit discourse relation recognition (IDRR) aims to recognize the discourse relation between two text segments without explicit connective. Although prompt learning-based approaches have achieved significant success in the IDRR task, these methods typically require carefully designed prompt templates for specific tasks, as well as auxiliary tasks that have a positive relationship with the main task, to enhance the performance of prompt learning. Recently, in-context learning (ICL) lets the input be prefaced by explicit guiding demonstrations, which can provide richer contextual information and mitigate its reliance on complex prompts and derived tasks. In this paper, we propose a COntrastive-based IN-context learning with Bias Calibration (COINBC) which utilizes contrastive learning for in-context learning and distinguishes between positive and negative demonstration samples. Additionally, we apply a bias calibration model based on the <i>k</i>-nearest-neighbor (<i>k</i>NN) calibration to mitigate the inherent biases in in-context learning. Experiments are conducted on the PDTB 3.0 corpus, and the results show that our proposed COINBC achieves new state-of-the-art performance for the IDRR task.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Contrastive-based In-context Learning with Bias Calibration for Implicit Discourse Relation Recognition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月24日

查看全文
  • Renyu Wang,
  • Bang Wang

摘要

Implicit discourse relation recognition (IDRR) aims to recognize the discourse relation between two text segments without explicit connective. Although prompt learning-based approaches have achieved significant success in the IDRR task, these methods typically require carefully designed prompt templates for specific tasks, as well as auxiliary tasks that have a positive relationship with the main task, to enhance the performance of prompt learning. Recently, in-context learning (ICL) lets the input be prefaced by explicit guiding demonstrations, which can provide richer contextual information and mitigate its reliance on complex prompts and derived tasks. In this paper, we propose a COntrastive-based IN-context learning with Bias Calibration (COINBC) which utilizes contrastive learning for in-context learning and distinguishes between positive and negative demonstration samples. Additionally, we apply a bias calibration model based on the k-nearest-neighbor (kNN) calibration to mitigate the inherent biases in in-context learning. Experiments are conducted on the PDTB 3.0 corpus, and the results show that our proposed COINBC achieves new state-of-the-art performance for the IDRR task.