0


高效识别分析的深层学习

Deep Learning for Efficient Discriminative Parsing
课程网址: http://videolectures.net/aistats2011_collobert_deep/  
主讲教师: Ronan Collobert
开课单位: 美国NEC实验室
开课时间: 2011-05-06
课程语种: 英语
中文简介:
提出了一种基于深度的自然语言分析快速纯判别算法。递归卷积图变压器网络(GTN)。假设一棵解析树被分解成一堆“级别”,网络会根据之前级别的预测来预测树的级别。仅使用几个基本的文本特性,我们就可以显示出与现有的纯判别解析器和现有的基准测试器相似的性能(F1分数)。解析器(如Collins解析器,基于概率上下文无关文法)具有巨大的速度优势。
课程简介: We propose a new fast purely discriminative algorithm for natural language parsing, based on a "deep" recurrent convolutional graph transformer network (GTN). Assuming a decomposition of a parse tree into a stack of "levels", the network predicts a level of the tree taking into account predictions of previous levels. Using only few basic text features, we show similar performance (in F1 score) to existing pure discriminative parsers and existing "benchmark" parsers (like Collins parser, probabilistic context-free grammars based), with a huge speed advantage.
关 键 词: 高效识别分析; 深层学习
课程来源: 视频讲座网
最后编审: 2021-05-14:yumf
阅读次数: 28