• Corpus ID: 72940850

Attribute Acquisition in Ontology based on Representation Learning of Hierarchical Classes and Attributes

  title={Attribute Acquisition in Ontology based on Representation Learning of Hierarchical Classes and Attributes},
  author={Tianwen Jiang and Ming Liu and Bing Qin and Ting Liu},
Attribute acquisition for classes is a key step in ontology construction, which is often achieved by community members manually. This paper investigates an attention-based automatic paradigm called TransATT for attribute acquisition, by learning the representation of hierarchical classes and attributes in Chinese ontology. The attributes of an entity can be acquired by merely inspecting its classes, because the entity can be regard as the instance of its classes and inherit their attributes… 

Figures and Tables from this paper

Fine-Grained Entity Typing for Relation-Sparsity Entities
This paper proposes a novel KG embedding model for relation-sparsity entities in KGs, where attributes could be granted with different weights according to an employed attention mechanism, while attribute values could be trained as bias vectors from attribute vectors pointing to type vectors.


Yago: a core of semantic knowledge
YAGO builds on entities and relations and currently contains more than 1 million entities and 5 million facts, which includes the Is-A hierarchy as well as non-taxonomic relations between entities (such as HASONEPRIZE).
CN-DBpedia: A Never-Ending Chinese Knowledge Extraction System
A never-ending Chinese Knowledge extraction system, CN-DBpedia, which can automatically generate a knowledge base that is of ever-increasing in size and constantly updated, and reduces the human costs by reusing the ontology of existing knowledge bases and building an end-to-end facts extraction model.
Learning Entity and Relation Embeddings for Knowledge Graph Completion
TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces by first projecting entities from entity space to corresponding relation space and then building translations between projected entities.
DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia
An overview of the DBpedia community project is given, including its architecture, technical implementation, maintenance, internationalisation, usage statistics and applications, including DBpedia one of the central interlinking hubs in the Linked Open Data (LOD) cloud.
Zhishi.me - Weaving Chinese Linking Open Data
This paper presents Zhishi.me, the first effort to publish large scale Chinese semantic data and link them together as a Chinese LOD (CLOD), and identifies important structural features in three largest Chinese encyclopedia sites for extraction and proposes several data-level mapping strategies for automatic link discovery.
Translating Embeddings for Modeling Multi-relational Data
TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
Knowledge Graph Embedding by Translating on Hyperplanes
This paper proposes TransH which models a relation as a hyperplane together with a translation operation on it and can well preserve the above mapping properties of relations with almost the same model complexity of TransE.
Multi-View Learning of Word Embeddings via CCA
Low Rank Multi-View Learning (LR-MVL) is extremely fast, gives guaranteed convergence to a global optimum, is theoretically elegant, and achieves state-of-the-art performance on named entity recognition (NER) and chunking problems.
Freebase: a collaboratively created graph database for structuring human knowledge
MQL provides an easy-to-use object-oriented interface to the tuple data in Freebase and is designed to facilitate the creation of collaborative, Web-based data-oriented applications.
WordNet: A Lexical Database for English
WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.