Modeling Relation Paths for Representation Learning of Knowledge Bases

By Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu. 2015

660 citations recorded by the source corpus.

Representation learning of knowledge bases aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a path-based representation learning model. This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, we design a path-constraint resource allocation algorithm to measure the reliability of relation paths. (2) We represent relation paths via semantic composition of relation embeddings. Experimental results on real-world datasets show that, as compared with baselines, our model achieves significant and consistent improvements on knowledge base completion and relation extraction from text. The source code of this paper can be obtained from https://github.com/mrlyk423/ relation_extraction.

Subfields: Artificial Intelligence

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

Citations in the corpus

Neural Programmer: Inducing Latent Programs with Gradient Descent (2015, methodology): “Neelakantan et al. (2015); Lin et al. (2015) learn simple Horn clauses in a large knowledge base using RNNs. Neural networks have also been used for Q&A on datasets that do not require complicated arithmetic and logic reasoning (Bordes et al., 2014; Iyyer et al., 2014; Sukhbaatar et al., 2015; Peng…”
SSE: Semantically Smooth Embedding for Knowledge Graphs (2017, background): “This section briefly reviews two lines of related work: KG embedding and manifold learning.”
Representation Learning of Knowledge Graphs with Hierarchical Types (2016, methodology): “For learning rate , we could select a fixed rate following [Bordes et al., 2013; Lin et al., 2015b] or design a flexible learning rate which will descend through iteration.”
Iterative Entity Alignment via Joint Knowledge Embeddings (2017, methodology): “Following [Lin et al., 2015], R(p|h, t) indicates the reliability of the path p given the entity pair (h, t).”
Multi-Modal Knowledge Graph Construction and Application: A Survey (2022, background): “Link prediction in MMKG [134], [136], [141], [142] aims to complete a triple (h, r, t) when one of the entities in h, r, t”
Representation Learning of Knowledge Graphs with Entity Descriptions (2016, background): “TransR (Lin et al. 2015b) models entities and relations in distinct semantic space and projects entities from entity space to relation space when learning embed-dings.”
Knowledge Graph Embedding for Link Prediction (2020, methodology): “PTransE [34] or, in our analysis, RSN [19]; some models do not employ paths directly in training but use them for additional tasks, as the explanation approach proposed by CrossE [72].”
Knowledge Graph Completion: A Review (2020, background): “For speciﬁc application, knowledge graph completion includes link prediction [11]–[13], entity prediction [14]–[16], relation prediction [17], attribute prediction [18] and other sub-tasks.”
Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences (2019, methodology): “ural language processing, such as the question answering [45], which accelerates the popularity of KGs. Although there are a host of methods for finding entities [4, 5] and their relations from texts [22], existing KGs are far from complete. Recent studies for KG completion show a great enthusiasm f”
On the Representation and Embedding of Knowledge Bases beyond Binary Relations (2016, methodology): “Recently knowledge base embedding[Bor-des et al. , 2013; Wang et al. , 2014; Lin et al. , 2015b; Bordes et al. , 2014b; 2011; Socher et al. , 2013; Lin et al. , 2015a] has stood out as an appealing and generic methodology to access various research problems in this area.”
SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions (2016, methodology): “To this end, a number of embedding methods have been proposed, such as TransE (Bordes et al. 2013), PTransE (Lin, Liu, and Sun 2015), KG2E (He et al. 2015), etc.”
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (2019, methodology): “IPTransE (Zhu et al., 2017) employs an iterative alignment process to extend PTransE (Lin et al., 2015a) for entity alignment.”
GAKE: Graph Aware Knowledge Embedding (2016, methodology): “We compare the proposed GAKE method with several state-of-art knowledge base embedding baselines, which includes NTN (Socher et al., 2013), TransE (Bordes et al., 2013), TransH (Wang et al., 2014), TransR (Lin et al., 2015b) and TransD (Ji et al., 2015).”
Open-World Knowledge Graph Completion (2017, methodology): “2013), TransR (Lin et al. 2015), TransH (Wang et al.”
Text-Enhanced Representation Learning for Knowledge Graph (2016, methodology): “TransE applies well to 1-to-1 relations but has issues for 1-to-N, N-to-1 and N-to-N relations.”
Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text (2016, methodology): “In contrast, using multi-step relation paths (e.g., husband ( barack , michelle ) ∧ mother ( michelle , sasha ) to train KB embeddings has been proposed very recently (Guu et al., 2015; Garcia-Duran et al., 2015; Lin et al., 2015; Neelakantan et al., 2015).”