Zero-shot Learning for Relation Extraction
@article{Gong2020ZeroshotLF, title={Zero-shot Learning for Relation Extraction}, author={Jiaying Gong and H. Eldardiry}, journal={ArXiv}, year={2020}, volume={abs/2011.07126} }
Most existing supervised and few-shot learning relation extraction methods have relied on labeled training data. However, in real-world scenarios, there exist many relations for which there is no available training data. We address this issue from the perspective of zero-shot learning (ZSL) which is similar to the way humans learn and recognize new concepts with no prior knowledge. We propose a zero-shot learning relation extraction (ZSLRE) framework, which focuses on recognizing novel… CONTINUE READING
Figures and Tables from this paper
References
SHOWING 1-10 OF 47 REFERENCES
Modeling Relations and Their Mentions without Labeled Text
- Computer Science
- ECML/PKDD
- 2010
- 809
- Highly Influential
- PDF
Improving Distantly-Supervised Relation Extraction with Joint Label Embedding
- Computer Science
- EMNLP/IJCNLP
- 2019
- 12
- PDF
Few-shot relation classification by context attention-based prototypical networks with BERT
- Computer Science
- EURASIP J. Wirel. Commun. Netw.
- 2020
- 1
ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages
- Computer Science
- ACL
- 2020
- 9
- PDF
RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
- Computer Science
- EMNLP
- 2018
- 85
- PDF
One-shot learning for fine-grained relation extraction via convolutional siamese neural network
- Computer Science
- 2017 IEEE International Conference on Big Data (Big Data)
- 2017
- 8
Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification
- Computer Science
- AAAI
- 2019
- 49
- Highly Influential
- PDF
FewRel: A Large-Scale Supervised Few-shot Relation Classification Dataset with State-of-the-Art Evaluation
- Computer Science, Mathematics
- EMNLP
- 2018
- 102
- Highly Influential
- PDF