Topical Word Embeddings
来源:互联网 发布:淘宝提升销量 编辑:程序博客网 时间:2024/05/21 18:39
论文 《 Topical Word Embeddings 》 记录
paper
code
Word Embedding面临的问题
homonymy and polysemy
解决homonymy and polysemy方法
multi-prototype: 对每个word赋予多个embedding
当前multi-prototype方法的缺点
1). These models generate multi-prototype vectors for each word in isolation, ignoring complicated correlations among words as well as their contexts. 说的很抽象
2). In multi-prototype setting, contexts of a word are divided into clusters with no overlaps. In reality, a word’s several senses may correlate with each other, and there is not clear semantic boundary between them.
解决上述缺点的方法(提出三个模型)
TWE三个模型的缺点
- TWE-1: TWE-1 does not consider the immediate interaction between a word and its assigned topic for learning(单词和主题向量没有直接的交互)
- TWE-2: TWE-2 considers the inner interaction of a word-topic pair by simply regarding the pair as a pseudo word, but it suffers from the sparsity issue because the occurrences of each word are rigidly discriminated into different topics.(假设单词在语料中出现N次, 每个主题下的单词平均只能学习到
N/T 次) - TWE-3: TWE-3 provides trade-off between discrimination and sparsity. But during the learning process of TWE-3, topic embeddings will influence the corresponding word embeddings, which may make those words in the same topic less discriminative.(
T<<W )
训练细节
Initialization is important for learning TWE models. In TWE-1, we first learn word embeddings using Skip-Gram. Afterwards, we initialize each topic vector with the average over all words assigned to this topics, and learn topic embeddings while keeping word embeddings unchanged. In TWE-2, we initialize the vector of each topic-word pair with the corresponding word vector from Skip-Gram, and learn TWE models. In TWE-3, we initialize word vectors using those from Skip-Gram, and topic vectors using those from TWE-1, and learn TWE models.
Experiments
Contextual Word Similarity
考虑到每个单词只有在上下文的条件下才可以区分, 所以在评价multi-prototype模型的时候,采用Contextual Word Similarity任务,试验结果如下:
个人总结: AvgSimC优于MaxSimC, 反映出单词之间的语义还是有交集的, 正如作者所说In reality, a word’s several senses may correlate with each other, and there is not clear semantic boundary between them;
Text Classification
macro-average and micro-average(precision, recall, F1-measure)
个人感觉只适用multi-class classification
二分类
precision=P, recall=R
多分类
n个二分类对应的precision和recall, 记为
注明:调和平均更重视较小值, 因为
试验结果:
- Topical Word Embeddings
- 【论文阅读】Topical Word Embeddings
- windons实现Yang Liu的Topical Word Embeddings
- word embeddings for text
- NLP:单词嵌入Word Embeddings
- Recurrent Neural Networks with Word Embeddings¶
- From Word Embeddings To Document Distances
- From Word Embeddings To Document Distances
- 【论文阅读】A Correlated Topic Model Using Word Embeddings
- sense2vec - a fast and accurate method for word sense disambiguation in neural word embeddings.
- Theano-Deep Learning Tutorials 笔记:Recurrent Neural Networks with Word Embeddings
- Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vector源码解析
- Reproducing and learning new algebraic operations on word embeddings using genetic programming
- Phn2vec Embeddings
- 「词嵌入」在自然语言处理中扮演什么角色?一文搞懂Word Embeddings的背后原理
- 论文读书笔记-using twitter to recommend real-time topical news
- Learning Structured Embeddings of Knowledge Bases-笔记
- Latent Embeddings for Zero-shot Classification
- vue的初步安装
- 关于checkbox的js传值和相关转换操作
- 什么是数据科学?数据科学的基本内容
- 干货 | 想学数据分析不知道该读什么书、从哪本读,翻遍专业知识类网站最全的整理!
- STL 源码分析之string(三)基础篇—insert,
- Topical Word Embeddings
- HDU 3687 National Day Parade(暴力)
- angular 4.*如何创建动态组件
- 人机交互专家齐聚,告诉你如何打造真正“自然”的人机交互 | CCF-ADL 重磅预告
- ansible学习笔记(一)
- DeepMind定下了一个小目标:用机器学习治疗癌症
- 坚果智能影院深圳线下体验会 试了才知多震撼
- 对AlamofireObjectMapper进行二次封装
- 小米手机下月也能用上MI Pay了,不过只限小米 5