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 2306.14822cs.CLcs.AI
收藏

用于细粒度情感分类的标签感知双曲嵌入

Label-Aware Hyperbolic Embeddings for Fine-grained Emotion Classification

UNC Chapel Hill(北卡罗来纳大学教堂山分校);Institute of Information Science, Academia Sinica(中央研究院信息科学研究所)

Chih-Yao Chen, Tun-Min Hung, Yi-Li Hsu, Lun-Wei Ku

AI总结:

提出HypEmo框架,通过在双曲空间中学习标签嵌入并计算样本与标签距离以加权交叉熵损失,有效捕捉标签层次结构,在细粒度情感分类任务上以更少参数和训练时间实现显著性能提升。

摘要:

细粒度情感分类(FEC)是一项具有挑战性的任务。具体而言,FEC需要处理标签之间微妙的差异,这些差异可能复杂且容易混淆。大多数现有模型仅在欧几里得空间中解决文本分类问题,我们认为这可能不是最优解,因为语义相近的标签(例如afraid和terrified)在该空间中可能无法被区分,从而损害性能。在本文中,我们提出了HypEmo,一个能够集成双曲嵌入以改进FEC任务的新颖框架。首先,我们在双曲空间中学习标签嵌入以更好地捕捉其层次结构,然后我们的模型将上下文化表示投影到双曲空间,以计算样本和标签之间的距离。实验结果表明,将这种距离纳入交叉熵损失进行加权,显著提升了性能且效率大幅提高。我们在两个基准数据集上评估了所提出的模型,发现与之前的最先进技术相比,实现了4.8%的相对提升,且参数量减少了43.2%,训练时间减少了76.9%。代码可在https://github.com/dinobby/HypEmo获取。

英文摘要:

Fine-grained emotion classification (FEC) is a challenging task. Specifically, FEC needs to handle subtle nuance between labels, which can be complex and confusing. Most existing models only address text classification problem in the euclidean space, which we believe may not be the optimal solution as labels of close semantic (e.g., afraid and terrified) may not be differentiated in such space, which harms the performance. In this paper, we propose HypEmo, a novel framework that can integrate hyperbolic embeddings to improve the FEC task. First, we learn label embeddings in the hyperbolic space to better capture their hierarchical structure, and then our model projects contextualized representations to the hyperbolic space to compute the distance between samples and labels. Experimental results show that incorporating such distance to weight cross entropy loss substantially improves the performance with significantly higher efficiency. We evaluate our proposed model on two benchmark datasets and found 4.8% relative improvement compared to the previous state of the art with 43.2% fewer parameters and 76.9% less training time. Code is available at https: //github.com/dinobby/HypEmo.

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。

↑