Search Results for author:
Found 9 papers, 1 papers with code
Distributional Negative Sampling for Knowledge Base Completion
State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities.
Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation
In addition to that, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations.
Hypernym Detection Using Strict Partial Order Networks
This paper introduces Strict Partial Order Networks (SPON), a novel neural network architecture designed to enforce asymmetry and transitive properties as soft constraints.
Automatic Taxonomy Induction and Expansion
The Knowledge Graph Induction Service (KGIS) is an end-to-end knowledge induction system.
Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer
However, there has been no attempt to exploit GNN to create taxonomies.
Open Knowledge Graphs Canonicalization using Variational Autoencoders
In this work, we propose Canonicalizing Using Variational Autoencoders (CUVA), a joint model to learn both embeddings and cluster assignments in an end-to-end approach, which leads to a better vector representation for the noun and relation phrases.
Type Prediction Systems
Inferring semantic types for entity mentions within text documents is an important asset for many downstream NLP tasks, such as Semantic Role Labelling, Entity Disambiguation, Knowledge Base Question Answering, etc.
Permutation Invariant Strategy Using Transformer Encoders for Table Understanding
Existing methods that leverage pretrained Transformer encoders range from a simple construction of pseudo-sentences by concatenating text across rows or columns to complex parameter-intensive models that encode table structure and require additional pretraining.
