您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks

文献类型： 会议论文

第一作者： Yingji Zhang

作者： Yingji Zhang 1 ; Danilo S. Carvalho 2 ; Andre Freitas 3 ;

作者机构： 1.Department of Computer Science, University of Manchester, United Kingdom

2.Department of Computer Science, University of Manchester, United Kingdom##National Biomarker Centre, CRUK-MI, Univ. of Manchester, United Kingdom

3.Department of Computer Science, University of Manchester, United Kingdom##Idiap Research Institute, Switzerland##National Biomarker Centre, CRUK-MI, Univ. of Manchester, United Kingdom

会议名称： [ "Annual Meeting of the Association for Computational Linguistics" , "Annual meeting of the Association for Computational Linguistics"]

主办单位：

页码： 2113-2134

摘要： Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in tasks such as image disentanglement, in the NLP domain sentence disentanglement is still comparatively under-investigated. Most previous work have concentrated on disentangling task-specific generative factors, such as sentiment, within the context of style transfer. In this work, we focus on a more general form of sentence disentanglement, targeting the localised modification and control of more general sentence semantic features. To achieve this, we contribute to a novel notion of sentence semantic disentanglement and introduce a flow-based invertible neural network (INN) mechanism integrated with a transformer-based language Au-toencoder (AE) in order to deliver latent spaces with better separability properties. Experimental results demonstrate that the model can conform the distributed latent space into a better semantically disentangled sentence space, leading to improved language interpretability and controlled generation when compared to the recent state-of-the-art language VAE models.

分类号： tp391

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台