- 博客(5)
- 收藏
- 关注
RSS订阅原创 [NLP-3] Part of Overview for Hypernym
Foreword Hypernym-hyponym (is-a) relation Definition: A noun X is a hyponym of a noun Y if X is a subtype or instance of Y. Thus “Shakespeare” is a hyponym of “author” (and conversely “author” is a ...
2019-07-09 08:32:28
643
原创 [GAN-1] Learning Note
Basic Idea of GAN When do we need GAN? Structured Learning Machine learning is to find a function f Regression: output a scalar Classification: class Structured learning / prediction: output a sequ...
2019-07-09 08:31:26
120
原创 [NLP-2] Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
Abstract Supervised learning such as WordNet, limits the coverage of these models Existed unsupervised methods do not scale to large vocabularies or yield poor accuracy This paper Introduce a meth...
2019-07-04 20:46:32
157
原创 [NLP] HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
OutlineAbstractIntroductionRelated WorksProblem FormulationThe HIEXPAN FrameworkFramework OverviewKey Term ExtractionTree ExpansionTaxonomy Global OptExperimentsSetupConclusionsFuture works Abstract I...
2019-07-04 17:23:52
482
原创 Basic Knowledge of Math
前言 本文记录了关于深度学习可能用到的一些线性代数背景知识，以供以后学习查阅。 章节浏览 向量 向量空间 矩阵 运算 范数 特征向量与特征值 梯度 向量 向量的含义在wiki中有如下解释，向量是向量空间中的一个元素。 Inmathematicsandphysics, avectoris an element of avector space. ...
2018-10-14 15:07:37
259
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