• Publications
  • Influence
Chinese Open Relation Extraction and Knowledge Base Establishment
TLDR
This article proposes a novel unsupervised linguistics-based Chinese ORE model based on Dependency Semantic Normal Forms (DSNFs), which can automatically discover arbitrary relations without any manually labeled datasets, and establishes a large-scale corpus of entity and relation. Expand
Supervised Neural Models Revitalize the Open Relation Extraction
TLDR
A hybrid neural sequence tagging model (NST) is proposed which combines BiLSTM, CNN and CRF to capture the contextual temporal information, local spatial information, and sentence level tag information of the sequence by using the word and part-of-speech embeddings. Expand
A review: Knowledge reasoning over knowledge graph
TLDR
The basic concept and definitions of knowledge reasoning and the methods for reasoning over knowledge graphs are reviewed, and the reasoning methods are dissected into three categories: rule- based reasoning, distributed representation-based reasoning and neural network-based Reasoning. Expand
Hybrid Neural Tagging Model for Open Relation Extraction.
TLDR
This paper builds a large-scale, high-quality training corpus in a fully automated way, and designs a tagging scheme to assist in transforming the ORE task into a sequence tagging processing, and proposes a hybrid neural network model (HNN4ORT) for open relation tagging. Expand
Study on the Chinese Word Semantic Relation Classification with Word Embedding
TLDR
The proposed method to the NLPCC 2017 shared task on Chinese word semantic relation classification won second place and can achieve competitive results with small training corpus. Expand
Triple Trustworthiness Measurement for Knowledge Graph
TLDR
A knowledge graph triple trustworthiness measurement model that quantify their semantic correctness and the true degree of the facts expressed and achieved significant and consistent improvements compared with other models. Expand
Learn#: A Novel incremental learning method for text classification
TLDR
A novel incremental learning strategy that has the advantage of a shorter training time than the One-Time model, because it only needs to train a new Student model each time, without changing the existing Student models. Expand
TTMF: A Triple Trustworthiness Measurement Frame for Knowledge Graphs
TLDR
A unified knowledge graph triple trustworthiness measurement framework to calculate the confidence values for the triples that quantify its semantic correctness and the true degree of the facts expressed is established. Expand
Knowledge Graph Embedding for Link Prediction and Triplet Classification
TLDR
The knowledge graph embedding method is applied to solve the specific tasks with Chinese knowledge base Zhishi.me to help solve the link prediction and triplet classification tasks. Expand
Chinese User Service Intention Classification Based on Hybrid Neural Network
TLDR
A hybrid neural network classification model based on BiLSTM and CNN is proposed to recognize users service intentions and can fuse the temporal semantics and spatial semantics of the user descriptions. Expand
...
1
2
3
...