用几何方法学习可组合的事件序列表示，让序列变成事件向量之和。
Event2Vec: A Geometric Approach to Learning Composable Representations of Event Sequences
- 基于加性递归结构学习可组合的向量表示
- 在布朗语料库上轮廓系数达0.0564，优于Word2Vec的0.0215
- 支持双曲空间建模层次数据，适合树状结构
神经表示研究日益揭示几何与拓扑结构的重要性。受此启发，我们提出Event2Vec，一种学习离散事件序列表示的新框架。模型采用简单的加性递归结构，学习可组合且可解释的嵌入。理论分析表明，在特定训练目标下，模型在欧几里得空间中的表示会收敛到理想的加性结构，即序列表示为各事件向量之和，这一性质称为线性加法假设。为克服欧几里得几何对层次数据的局限，我们还引入了双曲空间变体，其天然适合低失真地嵌入树状结构。实验验证了该假设：在布朗语料库上的定量评估显示，轮廓系数达0.0564，优于Word2Vec基线（0.0215），证明模型无需监督即可捕捉结构依赖关系。
原文摘要 · Abstract (English)
The study of neural representations, both in biological and artificial systems, is increasingly revealing the importance of geometric and topological structures. Inspired by this, we introduce Event2Vec, a novel framework for learning representations of discrete event sequences. Our model leverages a simple, additive recurrent structure to learn composable, interpretable embeddings. We provide a theoretical analysis demonstrating that, under specific training objectives, our model's learned representations in a Euclidean space converge to an ideal additive structure. This ensures that the representation of a sequence is the vector sum of its constituent events, a property we term the linear additive hypothesis. To address the limitations of Euclidean geometry for hierarchical data, we also introduce a variant of our model in hyperbolic space, which is naturally suited to embedding tree-like structures with low distortion. We present experiments to validate our hypothesis. Quantitative evaluation on the Brown Corpus yields a Silhouette score of 0.0564, outperforming a Word2Vec baseline (0.0215), demonstrating the model's ability to capture structural dependencies without supervision.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。