arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08598cs.CL
收藏

使用文本和图形矢量表示的分类学扩充

Taxonomy Enrichment with Text and Graph Vector Representations

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Lomonosov Moscow State University(莫斯科国立罗蒙诺索夫大学)

Irina Nikishina, Mikhail Tikhomirov, Varvara Logacheva, Yuriy Nazarov, Alexander Panchenko, Natalia Loukachevitch

摘要:

知识图谱,如DBpedia、Freebase或Wikidata,总是包含一个分类学的主干,允许根据次上位(“类-子类”)关系来安排和构建各种概念。随着特定领域词汇资源的快速增长,利用新词自动扩展现有知识库的问题变得越来越普遍。在本文中,我们解决的问题,分类丰富的目的是在现有的分类添加新词。我们提出了一种新的方法,可以实现高的结果,这项任务几乎没有努力。它使用大多数语言的现有资源,使该方法具有通用性。我们扩展了我们的方法,结合了图结构的深层表示,如node 2 vec,Poincaré嵌入,GCN等,最近在各种NLP任务上展示了有希望的结果。此外,结合这些表示与词嵌入,使我们能够击败最先进的状态。我们进行了全面的研究,现有的方法,以词和图形矢量表示和他们的融合方法的基础上的分类丰富。我们还探索了使用深度学习架构来扩展知识图谱的分类主干的方法。我们为英语和俄语的分类扩展创建了一些数据集。我们在不同的数据集上实现了最先进的结果,并提供了深入的错误分析。

英文摘要:

Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in accordance with the hypo-hypernym ("class-subclass") relationship. With the rapid growth of lexical resources for specific domains, the problem of automatic extension of the existing knowledge bases with new words is becoming more and more widespread. In this paper, we address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy. We present a new method that allows achieving high results on this task with little effort. It uses the resources which exist for the majority of languages, making the method universal. We extend our method by incorporating deep representations of graph structures like node2vec, Poincaré embeddings, GCN etc. that have recently demonstrated promising results on various NLP tasks. Furthermore, combining these representations with word embeddings allows us to beat the state of the art. We conduct a comprehensive study of the existing approaches to taxonomy enrichment based on word and graph vector representations and their fusion approaches. We also explore the ways of using deep learning architectures to extend the taxonomic backbones of knowledge graphs. We create a number of datasets for taxonomy extension for English and Russian. We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.

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。

↑