Kaijia Yang
ABSTRACT
Recently few-shot relation classification has drawn much attention. It devotes to addressing the long-tail relation problem by recognizing the relations from few instances. The existing metric learning methods aim to learn the prototype of classes and make prediction according to distances between query and prototypes. However, it is likely to make unreliable predictions due to the text diversity. It is intuitive that the text descriptions of relation and entity can provide auxiliary support evidence for relation classification. In this paper, we propose TD-Proto, which enhances prototypical network with relation and entity descriptions. We design a collaborative attention module to extract beneficial and instructional information of sentence and entity respectively. A gate mechanism is proposed to fuse both information dynamically so as to obtain a knowledge-aware instance. Experimental results demonstrate that our method achieves excellent performance.
Supplemental Material
- Razvan C Bunescu and Raymond J Mooney. 2005. A shortest path dependency kernel for relation extraction. In Proceedings of the conference on human language technology and empirical methods in natural language processing. 724--731.Google Scholar
Digital Library
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1. 4171--4186.Google Scholar
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017. 1126--1135.Google Scholar
- Tianyu Gao, Xu Han, Zhiyuan Liu, and Maosong Sun. 2019 a. Hybrid attention-based prototypical networks for noisy few-shot relation classification. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence,(AAAI-19), New York, USA. 6407--6414.Google ScholarDigital Library
- Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, and Jie Zhou. 2019 b. FewRel 2.0: Towards More Challenging Few-Shot Relation Classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China, 6251--6256.Google ScholarCross Ref
- Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2018. FewRel: A Large-Scale Supervised Few-shot Relation Classification Dataset with State-of-the-Art Evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018. 4803--4809.Google ScholarCross Ref
- Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. 2018. A Simple Neural Attentive Meta-Learner. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings.Google Scholar
- Tsendsuren Munkhdalai and Hong Yu. 2017. Meta networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017. 2554--2563.Google Scholar
- Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 1532--1543.Google ScholarCross Ref
- Victor Garcia Satorras and Joan Bruna Estrach. 2018. Few-Shot Learning with Graph Neural Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings.Google Scholar
- Jake Snell, Kevin Swersky, and Richard S. Zemel. 2017. Prototypical Networks for Few-shot Learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA. 4077--4087.Google Scholar
- Oriol Vinyals, Charles Blundell, Tim Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. 2016. Matching Networks for One Shot Learning. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain. 3630--3638.Google Scholar
- Markus Krötzsch. 2014. Wikidata: A Free Collaborative Knowledgebase. Communications of the Acm, Vol. 57, 10 (2014), 78--85.Google ScholarDigital Library
- Yaqing Wang and Quanming Yao. 2019. Few-shot learning: A survey. arXiv preprint arXiv:1904.05046 (2019).Google Scholar
- Zhi-Xiu Ye and Zhen-Hua Ling. 2019. Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28-August 2, 2019, Volume 1: Long Papers. 2872--2881.Google ScholarCross Ref
- Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. 2014. Relation Classification via Convolutional Deep Neural Network. In Proceedings of International Conference on Computational Linguistics. 2335--2344.Google Scholar
Index Terms
- Enhance Prototypical Network with Text Descriptions for Few-shot Relation Classification
Recommendations
Adaptive Prototype Network with Common and Discriminative Representation Learning for Few-Shot Relation Extraction
Advanced Data Mining and ApplicationsAbstractThe task of few-shot relation extraction presents a significant challenge as it requires predicting the potential relationship between two entities based on textual data using only a limited number of labeled examples for training. Recently, quite ...
Relational concept enhanced prototypical network for incremental few-shot relation classification
AbstractCompared with conventional close-domain relation classification, incremental few-shot relation classification requires incrementally to learn novel relations through very few samples without forgetting base relations, which is more fitting to the ...
Highlights- We propose a relational concept enhanced prototypical network to address incremental few-shot relation classification.
- We propose a base-class augmented contrastive learning method for forgetting problems.
- We propose incorporating ...
Few-shot relation classification by context attention-based prototypical networks with BERT
AbstractHuman-computer interaction under the cloud computing platform is very important, but the semantic gap will limit the performance of interaction. It is necessary to understand the semantic information in various scenarios. Relation classification (...
Comments