Utilizing Textual Information in Knowledge Graph Embedding: A Survey of Methods and Applications

Abstract

Techniques that map the entities and relations of the knowledge graph (KG) into a low-dimensional continuous space are called KG embedding or knowledge representation learning. However, most existing techniques learn the embeddings based on the facts in KG alone, suffering from the issues of imperfection and spareness of KG. Recently, the research on textual information in KG embedding has attracted much attention due to the rich semantic information supplied by the texts. Thus, in this paper, a survey of techniques for textual information based KG embedding is proposed. Firstly, we introduce the techniques for encoding the textual information to represent the entities and relations from perspectives of encoding models and scoring functions, respectively. Secondly, methods for incorporating the textual information in the existing embedding techniques are summarized. Thirdly, we discuss the training procedure of textual information based KG embedding techniques. Finally, applications of KG embedding with textual information in the specific tasks such as KG completion in zero-shot scenario, multilingual entity alignment, relation extraction and recommender system are explored. We hope that this survey will give insights to researchers into textual information based KG embedding. INDEX TERMS Knowledge graph embedding, textual information, text-based embedding, text-improved embedding, embedding-based applications.

Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion

“…In particular, we do not modify the scoring functions nor optimisation objectives for the respective KGE methods, which makes our proposed approach applicable in many existing KGE methods without any modifications. Text-Enhanced KGEs: Recently, a new line of research that combines textual information with relational graphs has emerged (Lu et al, 2020). Different combination methods have been proposed for this purpose.…”

“…Although previously proposed KGE methods have shown good empirical performances for KG completion (Minervini et al, 2015), the KGEs are learnt from the KGs only, which might not represent all the relations that exist between the entities included in the KG. To overcome this limitation, prior work has used external text corpora in addition to the KGs Xu et al, 2016;Long et al, 2016;Wang et al, 2019b,a;Lu et al, 2020). Compared to structured KGs, unstructured text corpora are abundantly available, up-to-date and have diverse linguistic expressions for extracting relational information.…”

Deep Graph Generators: A Survey

“…Related works. So far, several surveys have reviewed deep graph-related approaches such as those mainly focusing on graph representation learning methods [6], [72]- [78], graph attention models [79], knowledge graph research [80], [81], attack and defense techniques on graph data [82], and graph matching approaches [83], [84]. Although most of these surveys have made a passing reference to some modern graph generators, this field requires individual attention due to its value and growing popularity.…”

A Comprehensive Survey of Knowledge Graph-Based Recommender Systems: Technologies, Development, and Contributions

“…In addition, during the research, we came across studies that discuss knowledge graph applications in different domains [6,[21][22][23][24], and their advantages and disadvantages, but only some are oriented on the analysis of the technologies used, their development, and their method of evaluation.…”