Embedding/Chinese-Word-Vectors issues and pull requests

#170 - (Solved) schemes for fine-tuning with gensim / （已解决）使用 gensim 进行微调的方案

Issue - State: open - Opened by ShutterZor 29 days ago - 1 comment

#169 - 请问 Mixed-large 的 PPMI 向量的下载地址

Issue - State: open - Opened by rankiejiang 8 months ago - 1 comment

#168 - ValueError: could not convert string to float: '9:0.0221277913146'

Issue - State: open - Opened by Mp5A5 10 months ago - 1 comment

#167 - Wikipedia_zh 中文维基百科 SGNS 词的链接和谐了

Issue - State: closed - Opened by foxiyu about 1 year ago - 3 comments

#166 - 金融的四个链接全部失效了，请问有哪里可以下载吗？

Issue - State: closed - Opened by Sophiarong about 1 year ago - 2 comments

#165 - Wikipedia_zh 中文维基百科词300d 下载不了了

Issue - State: closed - Opened by prigioni over 1 year ago - 1 comment

#164 - 请问模型有上传到huggingface上吗

Issue - State: open - Opened by nezhazheng over 1 year ago

#163 - 如何对不同长度的句子生成固定维度的向量？

Issue - State: open - Opened by RockNHawk over 1 year ago - 3 comments

#162 - 如何加载模型

Issue - State: open - Opened by YiingWei over 1 year ago - 5 comments

#161 - embedding_sample/dense_small.txt在哪

Issue - State: open - Opened by tasty-dinasour over 1 year ago - 2 comments

#160 - MemoryError: Unable to allocate 1.47 TiB for an array with shape (635969, 635970) and data type float32

Issue - State: open - Opened by KevinYe553 over 1 year ago - 1 comment

#159 - embedding维度不统一问题

Issue - State: open - Opened by zhanghanweii over 1 year ago - 1 comment

#158 - Wikipedia_zh 中文维基百科词300d 下载不了了

Issue - State: open - Opened by sffan over 1 year ago - 1 comment

#157 - 网盘的提取码可以直接放到链接里面

Pull Request - State: closed - Opened by guofei9987 over 1 year ago - 1 comment

#156 - 没有找到预训练集的下载链接

Issue - State: closed - Opened by lastumr almost 2 years ago - 1 comment

#155 - 偏旁部首向量无法点击跳转到下载链接

Issue - State: open - Opened by xzy-1115 almost 2 years ago

#154 - 下游任务的词表中有些在你们的词向量文件中有未出现，请问有什么好的处理方式吗

Issue - State: open - Opened by zhengqingwu almost 2 years ago - 4 comments

#153 - 请问有汽车领域相关的词向量吗？

Issue - State: open - Opened by Peter-D-James about 2 years ago

#152 - Baidu Encyclopedia 百度百科-Word + Character + Ngram计算词与词之间的相似度很低

Issue - State: open - Opened by jiangpeng12345 about 2 years ago - 2 comments

#151 - Download from https://pan.baidu.com/ not possible without Chinese phone mumber

Issue - State: open - Opened by ihmsje about 2 years ago

#150 - Various Co-occurrence Information 里target word vector是什么

Issue - State: open - Opened by LuckyLiuM over 2 years ago - 1 comment

#149 - 如何读取sgns.financial.bigram-char

Issue - State: open - Opened by fredericky123 over 2 years ago - 2 comments

#148 - 请问这些词向量训练，使用的是什么分词器

Issue - State: closed - Opened by ArlanCooper about 3 years ago - 2 comments

#147 - 想问您一下fastText怎么使用您提供的这个预训练词向量

Issue - State: open - Opened by deepwebney about 3 years ago - 3 comments

#146 - 维度问题

Issue - State: closed - Opened by dlpansr about 3 years ago - 1 comment

#145 - 不支持语义运算

Issue - State: open - Opened by SnowyYANG about 3 years ago - 7 comments

#144 - 不同语料库训练的词向量是否可以通用？

Issue - State: open - Opened by Xiaqiannbu about 3 years ago - 9 comments

#143 - SGNS的Baidu Encyclopedia 百度百科的词、词 + N元组、词 + 字都是子向量

Issue - State: closed - Opened by yangjianhang over 3 years ago - 1 comment

#142 - 每个维度的意义

Issue - State: closed - Opened by Lanrzip over 3 years ago

#141 - 找不到词向量文件

Issue - State: open - Opened by liumiao-p over 3 years ago - 5 comments

#140 - 关于增量训练

Issue - State: open - Opened by sendRainAutumn over 3 years ago - 1 comment

#139 - 词向量文件加载错误

Issue - State: open - Opened by lxysl over 3 years ago - 2 comments

#138 - 作者麻烦咨询一下，您字词联合训练的流程是怎么实现的，是两个训练结束后拼接，还是字词一起输入模型进行训练，麻烦有时间解答一下，谢谢

Issue - State: closed - Opened by sijichangqing over 3 years ago - 1 comment

#137 - 四库全书语料库

Issue - State: closed - Opened by ruoyao-wang over 3 years ago - 1 comment

#136 - 添加中文版README

Pull Request - State: closed - Opened by zhc7 over 3 years ago - 1 comment

#135 - 请问能否提供四库全书的数据来源？

Issue - State: closed - Opened by zhc7 over 3 years ago - 1 comment

#134 - 文档中的词向量的下载链接失效，能麻烦重新提供一下吗

Issue - State: open - Opened by jingjingyinshen over 3 years ago - 3 comments

#133 - 关于<PAD>的问题

Issue - State: closed - Opened by AdamFocus over 3 years ago - 1 comment

#132 - 模型加载失败

Issue - State: closed - Opened by sunnychou0330 over 3 years ago - 1 comment

#131 - Various Co-occurrence Information 训练方式

Issue - State: open - Opened by wawltor almost 4 years ago - 1 comment

#130 - pretrained model的連結失效

Issue - State: open - Opened by mayritaspring almost 4 years ago - 2 comments

#129 - 符号"，"似乎缺失

Issue - State: closed - Opened by Zqjjjydl almost 4 years ago - 1 comment

#128 - PPMI模型维度问题

Issue - State: closed - Opened by ridiculousze almost 4 years ago - 1 comment

#127 - Literature 文学作品使用的书单可以分享一下吗？

Issue - State: closed - Opened by VisualJoyce almost 4 years ago - 1 comment

#126 - Literature 文学作品在文章中没有评测，是新增吗？

Issue - State: closed - Opened by VisualJoyce almost 4 years ago - 1 comment

#125 - 四库全书

Issue - State: closed - Opened by Crescentz almost 4 years ago - 2 comments

#124 - radical 部首 embed

Issue - State: closed - Opened by Crescentz almost 4 years ago - 6 comments

#123 - Baidu Pan links do not work.

Issue - State: closed - Opened by ktxlh almost 4 years ago - 2 comments

#122 - 其他问题

Issue - State: closed - Opened by Jf710001011 almost 4 years ago - 1 comment

#121 - 你好，表格中下载链接失效了

Issue - State: closed - Opened by LoveZyra almost 4 years ago

#120 - KeyError: '[SEP]'

Issue - State: closed - Opened by myf-algorithm about 4 years ago - 3 comments

#119 - word2vec中百度百科的Word + Character + Ngram 下载链接失效

Issue - State: closed - Opened by xpxpx about 4 years ago - 2 comments

#118 - 预训练向量的维度

Issue - State: closed - Opened by zzy-java about 4 years ago - 1 comment

#117 - 您好请问人民日报3.9G的语料如何获取呢？

Issue - State: closed - Opened by mzh1996 about 4 years ago

#116 - 如何查看词向量对应的词表？

Issue - State: closed - Opened by feijq over 4 years ago - 1 comment

#115 - 增量训练时，该怎么恢复缺失的字典树

Issue - State: closed - Opened by oshindow over 4 years ago - 1 comment

#114 - 请问这些语料的训练是基于什么分词的呢？

Issue - State: closed - Opened by littlefive5 over 4 years ago - 1 comment

#113 - load PPMI Word + Character + Ngram 报错

Issue - State: open - Opened by codescracker over 4 years ago - 2 comments

#112 - How the training sentence was segmented?

Issue - State: closed - Opened by a7744hsc over 4 years ago - 1 comment

#111 - 请问如何使用模型？

Issue - State: open - Opened by Ppaddington over 4 years ago - 2 comments

#110 - Requesting upload SGNS to Google Drive

Issue - State: open - Opened by hurui200320 over 4 years ago - 1 comment

#109 - 编码方式

Issue - State: closed - Opened by Yufei-Z over 4 years ago - 1 comment

#108 - 关于Financial News 金融新闻的词向量的异常word

Issue - State: closed - Opened by SaintLogos1234 over 4 years ago - 2 comments

#107 - 微博的原语料下载链接失效，能否告知微博数据的时间范围？

Issue - State: closed - Opened by omfoggynight over 4 years ago - 1 comment

#106 - 词向量在哪里？

Issue - State: closed - Opened by Jeeesie over 4 years ago - 1 comment

#105 - 请问语料的结构是怎样的呢？

Issue - State: closed - Opened by QiaowenYoung over 4 years ago - 1 comment

#104 - readme 为嘛不用中文？

Issue - State: closed - Opened by leixinhui over 4 years ago - 17 comments

#103 - <Baidu Encyclopedia 百度百科 300d>词表重复

Issue - State: open - Opened by yuboona almost 5 years ago - 11 comments

#102 - 能不能换个网盘呢？

Issue - State: closed - Opened by LuMelon almost 5 years ago - 2 comments

#101 - 你好，这些链接好像都打不开了，可以更新一下吗？谢谢！

Issue - State: closed - Opened by cuilp almost 5 years ago

#100 - 关于训练集数据

Issue - State: closed - Opened by hccngu almost 5 years ago - 1 comment

#99 - 能不能把词向量放到别的地方？

Issue - State: closed - Opened by marvinxu-free almost 5 years ago - 3 comments

#98 - Word Embedding with Baidu and Wikipedia

Issue - State: closed - Opened by EddieYang211 almost 5 years ago - 1 comment

#97 - sparse_small.txt　没有这个文件吗

Issue - State: closed - Opened by lion-han almost 5 years ago - 1 comment

#96 - 是否可以获取训练用 Corpus 资源？

Issue - State: closed - Opened by shenxuhui almost 5 years ago - 1 comment

#95 - 标点预测词向量的选择

Issue - State: open - Opened by shenxuhui almost 5 years ago - 1 comment

#94 - 想问一下字向量和词向量那个效果好

Issue - State: closed - Opened by leifei2012 almost 5 years ago - 1 comment

#93 - 你好，百度云的下载一直处于请求中，能否支持其他渠道的下载？

Issue - State: closed - Opened by lost-person almost 5 years ago - 2 comments

#92 - 训练语料

Issue - State: closed - Opened by akikaaa almost 5 years ago - 1 comment

#91 - 链接好像过期了，能再发下吗

Issue - State: closed - Opened by bigheary almost 5 years ago - 1 comment

#90 - 想问一下，这个向量，比较大，怎么裁剪呢？

Issue - State: open - Opened by dotsonliu almost 5 years ago - 2 comments

#89 - 作者你好，这个是否支持在我自己的语料上面，用word2vec模型再训练？？

Issue - State: open - Opened by dotsonliu almost 5 years ago - 14 comments

#88 - 字向量貌似挺重要，能开源单独的字向量就好了

Issue - State: closed - Opened by guotong1988 about 5 years ago - 1 comment

#87 - 请问为什么百度网盘下载一直是请求中

Issue - State: closed - Opened by AlbertChen1991 about 5 years ago - 1 comment

GitHub / Embedding/Chinese-Word-Vectors issues and pull requests