基于深度学习的区分性句法分析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: | 我们基于“深度”递归卷积图变换器网络(GTN),提出了一种用于自然语言解析的新型快速纯判别算法。假设将解析树分解为“级别”堆栈,则网络会考虑先前级别的预测来预测树的级别。仅使用很少的基本文本功能,我们就表现出与现有的纯判别解析器和现有的“基准”解析器(如Collins解析器,基于概率的上下文无关文法)相似的性能(在F1分数上),具有巨大的速度优势。 p> |
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: | 语言解析; 预测树 |
课程来源: | 视频讲座网 |
数据采集: | 2021-04-28:zyk |
最后编审: | 2021-05-14:yumf |
阅读次数: | 47 |