A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings
A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings
复制标题
DOI：
10.1145/3543507.3583310
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Song Jiang;Qiyue Yao;Qifan Wang;Yizhou Sun
中科院分区：
文献类型：
--
作者：
Song Jiang;Qiyue Yao;Qifan Wang;Yizhou Sun
分类法将知识分层组织，支持各种实际的Web应用，例如在线购物中的产品导航和社交平台上的用户配置文件标记。鉴于新实体的持续和快速出现，通过人工注释及时维护全面的分类法是非常昂贵的。因此，使用新实体自动扩展分类法是必不可少的。大多数现有的用于扩展分类法的方法将实体编码为向量嵌入（即，单点）。然而，我们认为，向量是不足以模拟的“是一个”层次分类（非对称关系），因为两个点只能代表成对的相似性（对称关系）。为此，我们建议将分类实体投影到框中（即，超矩形）。两个盒子可以是“包含”、“不相交”和“相交”的，因此自然代表了一个不对称的分类层次。在盒子嵌入的基础上，我们提出了一个新的分类扩展模型BoxTaxo。BoxTaxo的核心是学习实体的盒子，以捕获它们的子-父层次结构。为了实现这一点，BoxTaxo从几何和概率的联合视图优化了框嵌入。BoxTaxo还提供了一种简单而自然的推理方法：检查给定新实体的框是否完全封闭在现有分类法的候选父实体的框内。在两个基准上的大量实验证明了BoxTaxo与基于向量的模型相比的有效性。
Taxonomies, which organize knowledge hierarchically, support various practical web applications such as product navigation in online shopping and user profile tagging on social platforms. Given the continued and rapid emergence of new entities, maintaining a comprehensive taxonomy in a timely manner through human annotation is prohibitively expensive. Therefore, expanding a taxonomy automatically with new entities is essential. Most existing methods for expanding taxonomies encode entities into vector embeddings (i.e., single points). However, we argue that vectors are insufficient to model the “is-a” hierarchy in taxonomy (asymmetrical relation), because two points can only represent pairwise similarity (symmetrical relation). To this end, we propose to project taxonomy entities into boxes (i.e., hyperrectangles). Two boxes can be "contained", "disjoint" and "intersecting", thus naturally representing an asymmetrical taxonomic hierarchy. Upon box embeddings, we propose a novel model BoxTaxo for taxonomy expansion. The core of BoxTaxo is to learn boxes for entities to capture their child-parent hierarchies. To achieve this, BoxTaxo optimizes the box embeddings from a joint view of geometry and probability. BoxTaxo also offers an easy and natural way for inference: examine whether the box of a given new entity is fully enclosed inside the box of a candidate parent from the existing taxonomy. Extensive experiments on two benchmarks demonstrate the effectiveness of BoxTaxo compared to vector based models.