J
Jiang Wenbin
Researcher at Baidu
Publications - 11
Citations - 95
Jiang Wenbin is an academic researcher from Baidu. The author has contributed to research in topics: Context (language use) & Context model. The author has an hindex of 3, co-authored 11 publications receiving 56 citations.
Papers
More filters
Posted Content
CoKE: Contextualized Knowledge Graph Embedding.
Quan Wang,Huang Pingping,Haifeng Wang,Songtai Dai,Jiang Wenbin,Jing Liu,Yajuan Lyu,Zhu Yong,Hua Wu +8 more
TL;DR: Contextualized Knowledge Graph Embedding (CoKE) is presented, a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings.
Book ChapterDOI
DuIE: A Large-Scale Chinese Dataset for Information Extraction
Li Shuangjie,Wei He,Shi Yabing,Jiang Wenbin,Liang Haijin,Jiang Ye,Zhang Yang,Yajuan Lyu,Zhu Yong +8 more
TL;DR: This work designs an efficient coarse-to-fine procedure including candidate generation and crowdsourcing annotation, in order to achieve high data quality at a large data scale and builds a large-scale high-quality dataset, named DuIE, and makes it publicly available.
Patent
Mixed annotation learning neural network model, and training method and device of model
TL;DR: In this article, a mixed annotation learning neural network model is proposed, which consists of a first sub-network model and a second sub network model for encoding and decoding input data to generate initial result representation corresponding to the data to be processed.
Patent
Knowledge graph completion method and device, electronic equipment and storage medium
TL;DR: In this article, a knowledge graph completion method and a device, electronic equipment and a storage medium are described. And the method comprises the steps of obtaining view instances of a triple at different view angles; inputting the view instances into a target discrimination classification model, and obtaining a comprehensive classification result of the triad at all view angles.
Patent
Method and device for obtaining reading understanding material, electronic equipment and readable medium
TL;DR: In this article, a method for obtaining a reading understanding material, which comprises the steps: obtaining a subject-predicate-object triad which comprises a corresponding subject, a predicate and an object; according to a preset question template, constructing at least one question including a subject and a predicate of the subject-procedural object triad, and taking an object of the triad as an answer corresponding to the question.