Y
Yuanzhuo Wang
Researcher at Chinese Academy of Sciences
Publications - 129
Citations - 2152
Yuanzhuo Wang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Petri net & Embedding. The author has an hindex of 17, co-authored 121 publications receiving 1564 citations. Previous affiliations of Yuanzhuo Wang include Yanshan University & Tsinghua University.
Papers
More filters
Journal ArticleDOI
Significance and Challenges of Big Data Research
TL;DR: This position paper briefly introduces the concept of big data, including its definition, features, and value, and identifies from different perspectives the significance and opportunities that big data brings to us.
Proceedings ArticleDOI
Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention
TL;DR: This model first learns event detection oriented embeddings of documents through a hierarchical and supervised attention based RNN, and uses the learned document embedding to enhance another bidirectional RNN model to identify event triggers and their types in sentences.
Proceedings ArticleDOI
Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision
TL;DR: A neural method based on reinforcement learning, namely Stepwise Reasoning Network, is proposed, which formulates multi-relation question answering as a sequential decision problem and performs effective path search over the knowledge graph to obtain the answer, and leverages beam search to reduce the number of candidates significantly.
Proceedings Article
Locally adaptive translation for knowledge graph embedding
TL;DR: This paper proposes a locally adaptive translation method for knowledge graph embedding, called TransA, to find the optimal loss function by adaptively determining its margin over different knowledge graphs.
Proceedings ArticleDOI
Link Prediction on N-ary Relational Data
TL;DR: A method to conduct Link Prediction on N-ary relational data, thus called NaLP, is proposed, which explicitly models the relatedness of all the role-value pairs in the same n-ARY relational fact.