腾讯AI Lab开源大规模高质量中文词向量数据
腾讯AI Lab此次公开的中文词向量数据包含800多万中文词汇,其中每个词对应一个200维的向量。相比现有的中文词向量数据,腾讯AI L...NLP,MNIST Classification
39.4G
579
robot
354K
566
robot
8.49G
442
kambarakun
谷歌Word2Vec模型,包括 300 万个单词和短语的词汇表的单词向量
It’s 1.5GB! It includes word vectors for a vocabulary of 3 million words and phrases that they trained on roughly 100 b...Computer Science,Programming Classification
3.64G
335
Umberto
斯坦福大学的GloVe预训练的单词向量
GloVe is an unsupervised learning algorithm for obtaining vector representations for words. Training is performed on agg...Computer Science,Sports,Retail and Shopping Classification
989.9M
377
Mohamed Atef Khalaf
Facebook发布的300维预训练FastText英语单词向量
300-dimensional pretrained FastText English word vectors released by Facebook.The first line of the file contains the nu...NLP,Arts and Entertainment,Games Classification
4.52G
284
Vladimir Demidov
Facebook 发布的300维预训练,在 Common Crawl 上训练的200万个词向量
300-dimensional pretrained FastText English word vectors released by Facebook.The first line of the file contains the nu...NLP,Arts and Entertainment Classification
650M
360
Manish Maharjan
ConceptNet Numberbatch 向量,来自 ConceptNet 的词向量
These are the word vectors released by the Conceptnet project.ConceptNet的本质是一个三元组:...NLP Classification
899.91M
295
Nohman