Taxonomy completion, a task aimed at automatically enriching an existing taxonomy with new concepts, has gained significant interest in recent years. Previous works have introduced complex modules, external information, and pseudo-leaves to enrich the representation and unify the matching process of attachment and insertion. While they have achieved good performance, these introductions may have brought noise and unfairness during training and scoring. In this paper, we present TaxBox, a novel framework for taxonomy completion that maps taxonomy concepts to box embeddings and employs two probabilistic scorers for concept attachment and insertion, avoiding the need for pseudo-leaves. Specifically, TaxBox consists of three components: (1) a graph aggregation module to leverage the structural information of the taxonomy and two lightweight decoders that map features to box embedding and capture complex relationships between concepts; (2) two probabilistic scorers that correspond to attachment and insertion operations and ensure the avoidance of pseudo-leaves; and (3) three learning objectives that assist the model in mapping concepts more granularly onto the box embedding space. Experimental results on four real-world datasets suggest that TaxBox outperforms baseline methods by a considerable margin and surpasses previous state-of-art methods to a certain extent.

翻译：分类体系补全（Taxonomy Completion）是一项旨在利用新概念自动丰富现有分类体系的任务，近年来受到广泛关注。先前研究引入了复杂模块、外部信息及伪叶子节点以增强表示并统一附着与插入操作的匹配过程。尽管这些方法取得了良好性能，但此类引入可能带来训练与评分阶段的噪声及不公平性。本文提出TaxBox——一种新型分类体系补全框架，将分类体系概念映射至框嵌入，并通过两个概率评分器分别处理概念附着与插入操作，从而避免伪叶子节点的使用。具体而言，TaxBox包含三个组件：（1）图聚合模块，用于利用分类体系的结构信息，以及两个轻量级解码器，将特征映射至框嵌入并捕获概念间的复杂关系；（2）两个对应附着与插入操作的概率评分器，确保避免伪叶子节点；（3）三个学习目标，辅助模型在框嵌入空间中对概念进行更细粒度的映射。在四个真实世界数据集上的实验结果表明，TaxBox以显著优势优于基线方法，并在一定程度上超越了现有最优方法。