arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2301.04535cs.CLcs.SI
收藏

通过聚合多模态嵌入实现跨目标立场检测的少样本学习

Few-shot Learning for Cross-Target Stance Detection by Aggregating Multimodal Embeddings

Queen Mary University of London（伦敦玛丽女王大学）

Parisa Jamadi Khiabani, Arkaitz Zubiaga

备注：
To appear in IEEE Transactions on Computational Social Systems
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对跨目标少样本立场检测任务，提出聚合文本与网络多模态嵌入的CT-TN模型，在六种目标对上实现11%至21%的性能提升，验证了社会特征的有效性。

摘要：

尽管立场检测任务的受欢迎程度日益增加，但现有方法主要局限于使用社交媒体帖子的文本内容进行分类，忽略了该任务的社会属性。立场检测任务在跨目标分类场景中变得尤为具有挑战性，即使在少样本训练设置下，模型也需要对在训练期间仅见过少量相关样本的新目标进行立场预测。为了通过利用任务的社会属性来解决社交媒体中的跨目标立场检测问题，我们引入了 CT-TN，这是一种聚合源自数据文本和网络特征的多模态嵌入的新颖模型。我们在六种不同的源-目标对组合的少样本跨目标场景下进行了实验。通过将 CT-TN 与最先进的跨目标立场检测模型进行比较，我们证明了模型的有效性，在不同的基线模型上实现了从 11% 到 21% 的平均性能提升。使用不同数量样本的实验表明，CT-TN 在看到 300 个目标实例后能够优于其他模型。此外，消融实验证明了 CT-TN 各组件对最终性能的积极贡献。我们进一步分析了社交媒体用户之间的网络交互，揭示了使用社会特征进行跨目标立场检测的潜力。

英文摘要：

Despite the increasing popularity of the stance detection task, existing approaches are predominantly limited to using the textual content of social media posts for the classification, overlooking the social nature of the task. The stance detection task becomes particularly challenging in cross-target classification scenarios, where even in few-shot training settings the model needs to predict the stance towards new targets for which the model has only seen few relevant samples during training. To address the cross-target stance detection in social media by leveraging the social nature of the task, we introduce CT-TN, a novel model that aggregates multimodal embeddings derived from both textual and network features of the data. We conduct experiments in a few-shot cross-target scenario on six different combinations of source-destination target pairs. By comparing CT-TN with state-of-the-art cross-target stance detection models, we demonstrate the effectiveness of our model by achieving average performance improvements ranging from 11% to 21% across different baseline models. Experiments with different numbers of shots show that CT-TN can outperform other models after seeing 300 instances of the destination target. Further, ablation experiments demonstrate the positive contribution of each of the components of CT-TN towards the final performance. We further analyse the network interactions between social media users, which reveal the potential of using social features for cross-target stance detection.

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。

↑