Triple Trustworthiness Measurement for Knowledge Graph
- Shengbin Jia, Yang Xiang, Xiaojun Chen, Kun Wang, E. Shijia
- Computer ScienceThe Web Conference
- 13 May 2019
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.
SDT: An integrated model for open-world knowledge graph reasoning
- Xiaojun Chen, Shengbin Jia, Ling Ding, Hong Shen, Yang Xiang
- Computer ScienceExpert systems with applications
- 30 December 2020
Negative-supervised capsule graph neural network for few-shot text classification
- Ling Ding, Xiaojun Chen, Yang Xiang
- Computer ScienceJournal of Intelligent & Fuzzy Systems
- 28 August 2021
A negative-supervised capsule graph neural network (NSCGNN) which explicitly takes use of the similarity and dissimilarity between samples to make the text representations of the same type closer with each other and the ones of different types farther away, leading to representative and discriminative class prototypes.
Reasoning over temporal knowledge graph with temporal consistency constraints
- Xiaojun Chen, Shengbin Jia, Ling Ding, Yang Xiang
- Computer ScienceJournal of Intelligent & Fuzzy Systems
- 21 June 2021
This work presents TA-TransRILP, which involves temporal information by utilizing RNNs and takes advantage of Integer Linear Programming, and utilizes a character-level long short-term memory network to encode relations with sequences of temporal tokens, and combines it with common reasoning model.
Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text
- Shengbin Jia, Ling Ding, Xiaojun Chen, Yang Xiang
- Computer ScienceInternational Workshop on Natural Language…
- 1 April 2020
A model that specializes in identifying entities from Chinese social media text is proposed that alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of 2% over previous state-of-the-art methods.
TTMF: A Triple Trustworthiness Measurement Frame for Knowledge Graphs
- Shengbin Jia, Yang Xiang, Xiaojun Chen, E. Shijia
- Computer SciencearXiv.org
- 25 September 2018
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.
Parasitic Network: Zero-Shot Relation Extraction for Knowledge Graph Populating
- Shengbin Jia, E. Shijia, Ling Ding, Xiaojun Chen, Lingling Yao, Yang Xiang
- Computer ScienceInternational Conference on Database Systems for…
- 2021
Neighborhood aggregation based graph attention networks for open-world knowledge graph reasoning
- Xiaojun Chen, Ling Ding, Yang Xiang
- Computer ScienceJournal of Intelligent & Fuzzy Systems
- 31 July 2021
This work presents an attention-based method named as NAKGR, which leverages neighborhood information to generate entities and relations representations and performs well on the closed-world reasoning tasks.
MABERT: Mask-Attention-Based BERT for Chinese Event Extraction
- Ling Ding, Xiaojun Chen, Jian Wei, Yang Xiang
- Computer ScienceACM Transactions on Asian and Low-Resource…
- 19 May 2023
A mask-attention-based transformer augmented with two mask matrices is devised to replace the original one in BERT to avoid trigger-word mismatch and integrate lexical features into BERT layers directly.