Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning(论文解读)

Introduction(介绍)

本篇论文中,专注于探讨用于零样本谣言检测的有效提示方法,涉及语言和领域的转移。可以解耦共享的语义信息和特定语言中的句法偏差,从而增强提示与谣言数据之间的语义交互。此外,由于谣言的传播通常遵循空间和时间关系,这些关系提供了有关主张如何传播的有价值线索,而与特定领域无关。为此,提出了一种零样本响应感知提示学习(RPL)框架,用于在社交媒体上检测跨语言和跨领域的谣言。 

解释:

将共享的语义信息(文本的含义)和特定语言中的句法偏差(特定语言的语法结构差异)分开,不让它们混在一起。这样做的目的是为了在生成提示(prompt)和谣言数据之间建立更好的语义交互,不受特定语言的语法差异的干扰。

零样本谣言检测任务(ZRD)旨在将源谣言数据中学到的知识适应到目标数据中,而目标语言和领域中没有标记的训练样本。

具体流程:

训练时,模型接收一段文本,并在其中随机选择一些词汇进行掩盖。模型的任务是根据上下文预测这些被掩盖的词汇。然后进行预训练得到通用的语言表示。

Problem Statement and Background(问题陈述和背景)

在这项工作中,将零样本谣言检测任务定义为:给定一个源数据集,对目标数据集中的每个事件进行分类,判断其是否为谣言。源数据集和目标数据集来自不同的语言和领域。

具体而言:

源数据集,定义为一组事件表示为 $\mathcal{D}_{s}=\left\{C_{1}^{s}, C_{2}^{s}, \cdots, C_{M}^{s}\right\}$,每个事件是一个三元组表示为,其中表示一个真实性标签{谣言,非谣言}与主张(是某一事件或主题中的论述或陈述,它可以是一个观点、说法或声明)相关,以及理想情况下按时间顺序排列的所有相关响应微博帖子(m为响应帖子的数量)。

目标数据集,定义为一组事件表示为,每个事件是一个二元组表示为(与源数据集相似)。

这个任务可以被建模为一个监督分类问题,训练一个语言/领域无关的分类器 ,将从源数据集学到的特征迁移到目标事件,即

在这项工作中,我们将谣言检测转化为一种填空式掩码语言建模问题。例如,给定一个填空式模板 (例如,"For this [MASK] story." 作为提示,与主张 c 拼接成 $\hat{c}$),标准的提示学习利用预训练语言模型(PLMs)获取[MASK]令牌的隐藏状态,推断填充[MASK]的谣言指示性词语。

标签 $y$的概率为

公式解释:

其中$\mathcal{V}$是一组与谣言相关的标签词语,$\mathcal{V}_{y}$是与 $y$对应的 $\mathcal{V}$的子集,$g(\cdot)$是一个手动的语言表达器,将标签词语的概率转换为标签的概率。通过这种方式,我们可以将对[MASK]的预测词映射到真实性标签,从而对主张做出决策。

Approach(方法)

模型结构图: 

Response Ranking:

为了突显社交背景,增强事件的上下文表示学习,提出通过关注证据性响应来实现。核心思想是基于不同的传播线索对所有响应进行排名。

时间序列

假设随着时间的推移,响应性帖子对事件的态度会变得更倾向于一方,因此响应性帖子可以按照时间顺序和时间序列的反向顺序进行排序。分别为

按时间排序
### Few-Shot Learning Introduction Few-shot learning refers to a class of machine learning problems where the model is required to learn from very few examples, typically one or just a handful per category. This approach mimics human ability to generalize from limited data and has become an important area within deep learning research. The task layer's prior knowledge includes all methods that "learn how to learn," such as optimizing parameters for unseen tasks through meta-learning techniques which can provide good initialization for novel tasks[^1]. In this context: - **Meta-Learning**: Aims at designing models capable of fast adaptation with minimal training samples by leveraging previously acquired experience. - **Metric Learning**: Focuses on learning distance metrics between instances so similar ones are closer together while dissimilar remain apart in embedding space. #### Applications in Machine Learning One prominent application involves fine-grained classification using small datasets like Mini-ImageNet, demonstrating performance improvements when comparing different algorithms' embeddings propagation capabilities over time steps (Figure 7)[^2]. Another example comes from multi-label classification scenarios where combining MLP classifiers alongside KNN-based predictions enhances overall accuracy compared to traditional approaches relying solely upon prototype definitions derived directly from support sets during inference phases[^3]. Moreover, hybrid embedding strategies have been explored; these integrate both generalizable features learned across diverse domains along with specialized adjustments made specifically towards target-specific characteristics present only within given training distributions[Dtrain], thereby improving adaptability without sacrificing efficiency too much relative purely invariant alternatives[^4]. ```python def few_shot_classifier(embedding_model, classifier_type='mlp_knn'): """ Demonstrates a simple implementation outline for integrating Multi-layer Perceptron (MLP) and k-nearest neighbors (KNN). Args: embedding_model: Pre-trained neural network used to generate feature vectors. classifier_type: Type of final decision mechanism ('mlp', 'knn', or 'mlp_knn'). Returns: Combined prediction scores based on selected strategy. """ pass # Placeholder function body ``` --related questions-- 1. What specific challenges do few-shot learning systems face? 2. How does metric learning contribute to enhancing few-shot recognition abilities? 3. Can you explain more about the role of prototypes in few-shot classification schemes? 4. Are there any notable differences between MAML and other optimization-based meta-learning frameworks? 5. Which types of real-world problems benefit most significantly from applying few-shot learning methodologies?
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值