Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
复制标题
DOI：
10.1145/3447548.3467308
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Qingkai Zeng;Jinfeng Lin;W. Yu;J. Cleland-Huang;Meng Jiang
中科院分区：
文献类型：
--
作者：
Qingkai Zeng;Jinfeng Lin;W. Yu;J. Cleland-Huang;Meng Jiang
分类的自动构建支持电子商务、网络搜索和问题回答中的许多应用。现有的分类扩展或完成方法假设已经准确地提取了新的概念，并且从文本语料库学习了它们的嵌入向量。然而，修复分类的不完全性的一个关键和根本的挑战是提取的概念的不完备性，特别是对于那些名称具有多个单词的概念，因此在语料库中出现的频率很低。为了解决基于抽取的方法的局限性，我们建议GenTaxo通过识别现有分类中需要新概念的位置，然后生成适当的概念名称来增强分类完成。GenTaxo不依赖语料库进行概念嵌入，而是从周围基于图形和语言的关系信息中学习上下文嵌入，并利用语料库预先训练概念名称生成器。实验结果表明，与现有的分类方法相比，GenTaxo提高了分类的完备性。
Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering. Existing taxonomy expansion or completion methods assume that new concepts have been accurately extracted and their embedding vectors learned from the text corpus. However, one critical and fundamental challenge in fixing the incompleteness of taxonomies is the incompleteness of the extracted concepts, especially for those whose names have multiple words and consequently low frequency in the corpus. To resolve the limitations of extraction-based methods, we propose GenTaxo to enhance taxonomy completion by identifying positions in existing taxonomies that need new concepts and then generating appropriate concept names. Instead of relying on the corpus for concept embeddings, GenTaxo learns the contextual embeddings from their surrounding graph-based and language-based relational information, and leverages the corpus for pre-training a concept name generator. Experimental results demonstrate that GenTaxo improves the completeness of taxonomies over existing methods.