Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications

Wei Zhao, Haiyun Peng, Steffen Eger, Erik Cambria, Min Yang
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes. In this paper, we introduce (i) an agreement score to evaluate the performance of routing processes at instance level; (ii) an adaptive optimizer to enhance the reliability of routing; (iii) capsule compression and partial routing to improve the scalability of capsule networks. We validate our approach on two NLP tasks,
more » ... ly: multi-label text classification and question answering. Experimental results show that our approach considerably improves over strong competitors on both tasks. In addition, we gain the best results in low-resource settings with few training instances. 1 Jerry completed his project. Jerry managed to finish his project. Jerry succeeded in finishing his project. Extrapolate Extrapolated sentences Unseen sentences Observed sentences Extrapolate operation Extrapolation regime Jerry is sleeping.
doi:10.18653/v1/p19-1150 dblp:conf/acl/ZhaoPECY19 fatcat:4cqppc7j55gqhbiopxywpyvfiq