Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts.
However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity).
To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.
It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s).
Information selection is the most important component in document summarization task.
Ranked #22 on Abstractive Text Summarization on CNN / Daily Mail
Recent neural sequence-to-sequence models have shown significant progress on short text summarization.
Ranked #33 on Abstractive Text Summarization on CNN / Daily Mail
Document-level information is very important for event detection even at sentence level.
Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure.
Knowledge graph embedding aims to embed entities and relations of knowledge graphs into low-dimensional vector spaces.
Ranked #1 on Link Prediction on WN18 (filtered)
Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space.