Improved Knowledge Base Completion by Path-Augmented TransR Model

Knowledge base completion aims to infer new relations from existing information. In this paper, we propose path-augmented TransR (PTransR) model to improve the accuracy of link prediction. In our approach, we base PTransR model on TransR, which is the best one-hop model at present. Then we regularize TransR with information of relation paths. In our experiment, we evaluate PTransR on the task of entity prediction. Experimental results show that PTransR outperforms previous models.

• Publication year

  2016

• Venue

  arXiv.org

• Publication date

  2016-10-06

• Fields of study

  Computer Science

• Identifiers
  arXiv 1610.04073
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Text-Enhanced Representation Learning for Knowledge Graph

  2016cited by this paper
• Improved relation classification by deep recurrent neural networks with data augmentation

  2016cited by this paper
• Learning Entity and Relation Embeddings for Knowledge Graph Completion

  2015influential reference
• Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths

  2015cited by this paper
• Natural Language Inference by Tree-Based Convolution and Heuristic Matching

  2015cited by this paper
• Modeling Relation Paths for Representation Learning of Knowledge Bases

  2015influential reference
• Classifying Relations by Ranking with Convolutional Neural Networks

  2015cited by this paper
• Traversing Knowledge Graphs in Vector Space

  2015cited by this paper
• Information Extraction over Structured Data: Question Answering with Freebase

  2014cited by this paper
• Knowledge Graph Embedding by Translating on Hyperplanes

  2014influential reference
• Reasoning With Neural Tensor Networks for Knowledge Base Completion

  2013cited by this paper
• Linguistic Regularities in Continuous Space Word Representations

  2013cited by this paper
• Translating Embeddings for Modeling Multi-relational Data

  2013influential reference
• Learning and inferencing in user ontology for personalized Semantic Web search

  2009cited by this paper
• Freebase: a collaboratively created graph database for structuring human knowledge

  2008cited by this paper
• Extracting Lexical Semantic Knowledge from Wikipedia and Wiktionary

  2008cited by this paper
• Open Information Extraction from the Web

  2007cited by this paper
• A Survey of Web Information Extraction Systems

  2006cited by this paper
• Gene Ontology: tool for the unification of biology

  2000cited by this paper
• WordNet: A Lexical Database for English

  1995cited by this paper
• Automatic Acquisition of Hyponyms from Large Text Corpora

  1992cited by this paper

• Incorporating Dynamic Logic Alignment into Knowledge Graph Reasoning Based on Reinforcement Learning

  2025cites this paper
• Knowledge interaction graph attention network for multi-behavior recommendation

  2025cites this paper
• Pre-training and Diagnosing Knowledge Base Completion Models

  2024cites this paper
• A Representation Learning Approach Incorporating Entity Descriptions and Types

  2023cites this paper
• A Renovated CNN-Based Model Enhances KGC Task Performance

  2022cites this paper
• RLPath: a knowledge graph link prediction method using reinforcement learning based attentive relation path searching and representation learning

  2021cites this paper
• Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

  2020cites this paper
• Multilingualization of Medical Terminology: Semantic and Structural Embedding Approaches

  2020cites this paper
• Improving Knowledge Graph Embedding Using Locally and Globally Attentive Relation Paths

  2020cites this paper
• Knowledge Representation Learning with Dynamic Path

  2019cites this paper
• Embedded Word Representations for Rich Indexing: A Case Study for Medical Records

  2018cites this paper