- 博客(3)
- 收藏
- 关注
原创 读《DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization》
组会讲的论文,AAAI-19的一个工作,记一记 任务:文本摘要生成 方法: Extractive 基于分类,判断文章每一句话属不属于摘要 Abstractive 基于生成,常用的框架是encoder-decoder “Most of these deep summarization models aim to learn a direct mapping from the document t...
2018-11-17 11:20:44
666
原创 慢慢读《Deep Learning In Natural Language Processing》(二)
本章讨论CLU(conversation language understanding) 1、introduction && historical perspective 2、major language understanding tasks domain detection or intent determination 任务描述:classifying a given ...
2018-11-09 20:20:59
628
原创 慢慢读《Deep Learning In Natural Language Processing》(一)
第一次浪潮:Rationalism “The approaches, based on the belief that knowledge of language in the human mind is fixed in advance by generic inheritance” 例证:特定领域的专家系统(exper system) 缺点:过分依...
2018-11-08 20:51:21
901
2
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人