JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments. To tackle these problems, we propose a graph-text joint representation learning model called JointGT. During encoding, we devise a structure-aware semantic aggregation module which is plugged into each Transformer layer to preserve the graph structure. Furthermore, we propose three new pre-training tasks to explicitly enhance the graph-text alignment including respective text / graph reconstruction, and graph-text alignment in the embedding space via Optimal Transport. Experiments show that JointGT obtains new state-of-the-art performance on various KG-to-text datasets.
Code (1)
Tasks
Graph ReconstructionKG-to-Text GenerationKnowledge GraphsQuestion GenerationRepresentation LearningText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Joint Video and Text Parsing for Understanding Events and Answering Queries
We propose a framework for parsing video and text jointly for understanding events and answering user queries. Our framework produces a parse graph that represents the compositional structures of spatial information (obj…
Semantic ParsingJoint Representation Learning of Text and Knowledge for Knowledge Graph Completion
Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately. In this work, we propose a novel framework to embed words, entities an…
General ClassificationKnowledge Graph CompletionPredictionRelation+3Graph-Text Multi-Modal Pre-training for Medical Representation Learning
As the volume of Electronic Health Records (EHR) sharply grows, there has been emerging interest in learning the representation of EHR for healthcare applications. Representation learning of EHR requires appropriate mode…
Representation LearningConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings
Learning on text-attributed graphs (TAGs), in which nodes are associated with one or more texts, has been the subject of much recent work. However, most approaches tend to make strong assumptions about the downstream tas…
Community DetectionContrastive LearningGraph Neural NetworkLanguage Modeling+3Detecting Objects with Context-Likelihood Graphs and Graph Refinement
The goal of this paper is to detect objects by exploiting their interrelationships. Contrary to existing methods, which learn objects and relations separately, our key idea is to learn the object-relation distribution jo…
Objectobject-detectionObject DetectionRelation