中国科大学位与研究生教育
课程名称: 教师:
当前位置:
 >> 
 >> 
深度自然语言建模张量积生成网络
深度自然语言建模张量积生成网络
教师介绍

本讲教师:吴大鹏
所属学科:工科
人  气:357

课程介绍
摘要:In this talk, I present a new approach to the design of deep networks for natural language processing (NLP), based on the general technique of Tensor Product Representations (TPRs) for encoding and processing symbol structures in distributed neural networks. A network architecture--- the Tensor Product Generation Network (TPGN) --- is proposed which is capable in principle of carrying out TPR computation, but which uses unconstrained deep learning to design its internal representations. Instantiated in a model for image-caption generation, TPGN outperforms LSTM baselines when evaluated on the COCO dataset. The TPR-capable structure enables interpretation of internal representations and operations, which prove to contain considerable grammatical content. Our caption-generation model can be interpreted as generating sequences of grammatical categories and retrieving words by their categories from a plan encoded as a distributed representation.

评论

针对该课程没有任何评论,谈谈您对该课程的看法吧?
  • 用户名: 密 码:
致谢:本课件的制作和发布均为公益目的,免费提供给公众学习和研究。对于本课件制作传播过程中可能涉及的作品或作品部分内容的著作权人以及相关权利人谨致谢意!
课件总访问人次:16736748
中国科学技术大学研究生网络课堂试运行版,版权属于中国科学技术大学研究生院。
本网站所有内容属于中国科学技术大学,未经允许不得下载传播。
地址:安徽省合肥市金寨路96号;邮编:230026。TEL:+86-551-63602922;E-mail:wlkt@ustc.edu.cn。