欢迎访问江苏省计算机学会网站!    设为首页  |  收藏本站
江苏省计算机学会
  •  当前位置首页 > 新闻中心 > 通知公告
    新闻中心  
    学会动态
    政策法规
    行业新闻
    图片新闻
    通知公告
     
    通知公告
    技术创新论坛 Recent work on Natural Language Generation
    发布时间:2019-09-04 09:17:33
    南京大学计算机科学与技术系
    软件新技术与产业化协同创新中心

    摘 要:
    Natural language generation has been a fundamental technology in many applications such as machine writing, machine translation, chatbots, etc. In this talk, we will begin from the taxonomy of current deep generative models for text generation, then introduce our recent work in different branches. State-of-the-art text generation models employ neural networks such as RNN and Transformer to parameterize the density of text in an auto-regressive fashion, because the density of sentences is intractable for its exponential space. We will first introduce some advanced approaches to better factorize the density. Then we turn to the variational auto-encoders (VAE), which approximates the density of sentences with variational inference. Our recent work incorporates syntax latent variables to improve the quality of texts from VAE. We also propose a DGMVAE for interpretable text generation. Finally, different to previous approaches with explicit density of sentences, we explore a novel Markov Chain Monte Carlo approach called CGMH for constrained text generation, which does not keep an explicit density of sentences and generates sentences abandoning the left-to-right fashion. CGMH could also be used for generating fluent adversarial examples of text.
    报告人简介:
    Dr. Hao Zhou is a researcher at ByteDance AI Lab. His research interests are machine learning and its applications for natural language processing, including syntax parsing, machine translation and text generation. Currently he focuses on deep generative models for NLP. Previously he received his Ph.D. degrees in 2017, from Nanjing University. He has served in the Program Committee for ACL, EMNLP, IJCAI, AAAI, NIPS. He has more than 20 publications in prestigious conferences and journals, including ACL, EMNLP, NAACL, TACL, AAAI, IJCAI, NIPS and JAIR. He will give tutorials on deep generative model for text generation at NLPCC’19 and discreteness of neural NLP at EMNLP’2019 (Homepage: https://zhouh.github.io/).
    时间:9月6日(星期五) 14:00
    地点:计算机科学技术楼230室

    上一篇:CSAI 卓越科学家大讲堂 联邦学习与人工智能
    下一篇:学术报告Cost Effective Data Placement in the Cloud for Efficient Data Access of Online Social Networks
    友情链接:
    江苏省科学技术协会 中国计算机学会 南京大学 南京大学计算机科技与技术系 南京大学软件学院 东南大学计算机科学与工程学院 江苏经贸职业技术学院 南京信息职业技术学院 南京工业职业技术学院 江苏海事职业技术学院 常州信息职业技术学院 国网电力科学研究院 电子科技集团第28研究所 江南计算技术研究所 
       
     

    Copyright (c) 版权所有 江苏省计算机学会         【后台管理】    南京网站建设公司
    秘书处办公室       地址: 江苏省南京市仙林大道163号  邮编:210023   电话/传真:025-89680909   
    秘书处市内联络点   地址: 江苏省南京市汉口路22号     邮编:210093   电话/传真:025-86635622
    电子邮箱:jscs@nju.edu.cn   网址:www.jscs.org.cn    技术支持:南京成旭通信息技术有限公司  

    网站备案号:苏ICP备14049275号

    您是本站第5401697位来客!

    在线客服

    点击这里给我发消息