SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

By Han Xiao, Minlie Huang, Lian Meng, Xiaoyan Zhu. 2016

196 citations recorded by the source corpus.

Knowledge graph embedding represents entities and relations in knowledge graph as low-dimensional, continuous vectors, and thus enables knowledge graph compatible with machine learning models. Though there have been a variety of models for knowledge graph embedding, most methods merely concentrate on the fact triples, while supplementary textual descriptions of entities and relations have not been fully employed. To this end, this paper proposes the semantic space projection (SSP) model which jointly learns from the symbolic triples and textual descriptions. Our model builds interaction between the two information sources, and employs textual descriptions to discover semantic relevance and offer precise semantic embedding. Extensive experiments show that our method achieves substantial improvements against baselines on the tasks of knowledge graph completion and entity classification.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “[59] embed a knowledge graph from both the knowledge graph triplets and the textual descriptions of entities and relations.”
KG-BERT: BERT for Knowledge Graph Completion (2019, background): “Text-enhanced models DKRL and SSP can also outperform structure only methods TransE and TransH.”
Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion (2020, methodology): “when the entity description is included [38, 45].”
Knowledge Graph Embedding Based Question Answering (2019, background): “Several work [14, 40, 41] explored to advance TransE, either via taking relation mentions in corpus into consideration [14, 40], or via projecting predicate/entity representations into a semantic hyperplane learned from the topic model [41].”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “The semantically-enriched representation models like NTN (Socher et al., 2013), SSP (Xiao et al., 2017) and DKRL (Xie et al., 2016) combine semantic information into the representation of entities and relations.”
Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “See [102], [103], [104], [105] for other approaches where textual information is also considered.”
Augmenting Neural Machine Translation with Knowledge Graphs (2019, background): “More work on agglutinating the semantics with entities arose, such as SSP (Xiao et al., 2017) and DKRL (Xie et al., 2016a) as well as TKRL (Xie et al., 2016b).”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “SSP [66] captures the strong correlations between triples and textual descriptions by projecting them in a semantic subspace.”