Embedding/Chinese-Word-Vectors issues and pull requests

#70 - 你好，请问词向量是用什么方法进行的分词？？

Issue - State: closed - Opened by wzs951015 over 5 years ago - 1 comment

#69 - 评估命令中的参数问题

Issue - State: closed - Opened by EdQzz over 5 years ago - 1 comment

#68 - 请问词向量文件在哪儿

Issue - State: closed - Opened by wangdomg over 5 years ago - 2 comments

#67 - how to load w2v with multi thread

Issue - State: closed - Opened by xiongma over 5 years ago - 2 comments

#66 - 关于《四库全书》的字向量是否少字的问题

Issue - State: closed - Opened by LudoArt over 5 years ago - 2 comments

#65 - 您好请问词向量里有没有<SOS> <EOS>等结束开始符啥的？

Issue - State: open - Opened by wudejian789 over 5 years ago - 2 comments

#64 - Reducing the embedding size

Issue - State: closed - Opened by Riccorl over 5 years ago - 1 comment

#63 - 词向量文件中词的排列顺序有什么规律么？

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

#62 - 使用CAD8评估效果不理想

Issue - State: closed - Opened by zxyangyu over 5 years ago - 3 comments

#61 - 词向量文件在哪？

Issue - State: closed - Opened by kkkeiko over 5 years ago

#60 - 请问有处理之后的纯文本的语料吗？以及处理他们的程序

Issue - State: open - Opened by flyboyer over 5 years ago - 7 comments

#59 - 字表和词表的覆盖范围

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

#58 - 加载词向量时出现大量警告

Issue - State: closed - Opened by yewenjunfighting over 5 years ago - 2 comments

#57 - Can you provide other links to download?

Issue - State: open - Opened by ThiagoSousa over 5 years ago - 7 comments

#56 - 下载语料后，出现ValueError: array is too big; `arr.size * arr.dtype.itemsize` is larger than the maximum possible size.错误

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

#55 - 复现结果，方便提供一下预处理过的百度百科预料么

Issue - State: closed - Opened by MLjian almost 6 years ago - 1 comment

#54 - 请问对于未登录词如何计算？

Issue - State: open - Opened by Au3C2 almost 6 years ago - 3 comments

#53 - eval question

Issue - State: open - Opened by flyboyer almost 6 years ago - 4 comments

#52 - 請問有支援繁體中文嗎？

Issue - State: open - Opened by allenyllee almost 6 years ago - 1 comment

#51 - 感觉模型效果没有cbow好呢

Issue - State: closed - Opened by csanycall about 6 years ago - 1 comment

#50 - PPMI

Issue - State: closed - Opened by sunnychou0330 about 6 years ago - 2 comments

#49 - 下载的词向量文件，怎么变成word2vec模型文件，并且支持增量训练

Issue - State: closed - Opened by lijc210 about 6 years ago - 1 comment

#48 - 請問表格中的連結失效了??? (300d/Sparse)

Issue - State: open - Opened by p06922001 about 6 years ago - 3 comments

#47 - Word+Character+Ngram问题

Issue - State: closed - Opened by jeffery-zhougang about 6 years ago - 1 comment

#46 - Download link not available

Issue - State: closed - Opened by fireflyHunter about 6 years ago - 1 comment

#45 - 如何使用这些模型呢？

Issue - State: closed - Opened by cooljacket about 6 years ago - 5 comments

#44 - How to define a basic line of "good word2vec"

Issue - State: open - Opened by zhouxincheng about 6 years ago - 2 comments

#43 - how to get the corpus like 'Financial News 金融新闻'?

Issue - State: open - Opened by SeekPoint about 6 years ago - 1 comment

#42 - 網盤不存在

Issue - State: closed - Opened by lyn5466 about 6 years ago - 1 comment

#41 - 特殊字符的词向量

Issue - State: closed - Opened by xuenhappy about 6 years ago - 3 comments

#40 - 词向量选择的target都是word吗？只不过context是word、word+char、word+ngram、word+char+ngram

Issue - State: closed - Opened by PuddingCoder about 6 years ago - 1 comment

#39 - 大佬，如果想获取某个字符的词嵌入，应该用什么语句啊

Issue - State: closed - Opened by Xshelton about 6 years ago - 2 comments

#38 - SGNS和PPMI的word+char+ngram的CA8评估效果为什么没有在论文里写出来呢？如果有可以放出来吗？

Issue - State: closed - Opened by PuddingCoder about 6 years ago - 1 comment

#37 - Why I just find 260k vocabulary in Zhihu_QA but you said there are 1117K?

Issue - State: closed - Opened by Dragon2333 over 6 years ago - 1 comment

#36 - 能把训练词向量的代码开源一下嘛

Issue - State: closed - Opened by qujinqiang over 6 years ago - 3 comments

#35 - Cannot download the pre-trained vector files

Issue - State: closed - Opened by dx80232 over 6 years ago - 3 comments

#34 - can't use word2vec.load()?

Issue - State: closed - Opened by chencjiajy over 6 years ago - 1 comment

#33 - 词向量的文件为什么这么大啊

Issue - State: closed - Opened by bioRichard over 6 years ago - 2 comments

#32 - 詞向量下載連結失效？

Issue - State: closed - Opened by ipodtouch64g over 6 years ago - 4 comments

#31 - 关于语料预处理

Issue - State: closed - Opened by helenxu over 6 years ago - 1 comment

#30 - 增量训练问题

Issue - State: closed - Opened by WaaterD over 6 years ago - 1 comment

#29 - 词向量文件无法load

Issue - State: closed - Opened by zhenghaor10 over 6 years ago - 3 comments

#28 - 下载的词向量无法解压

Issue - State: closed - Opened by luffywalf over 6 years ago - 1 comment

#27 - 原始用于训练的语料数据会公开不？

Issue - State: closed - Opened by guotong1988 over 6 years ago - 2 comments

#26 - 分词词库问题

Issue - State: open - Opened by godfatherzzx over 6 years ago - 1 comment

#25 - 建议对英文词进行大小写归一化处理

Issue - State: closed - Opened by boringcoder over 6 years ago - 1 comment

#24 - 编码问题

Issue - State: closed - Opened by fabyangliu over 6 years ago - 1 comment

#23 - 请问是否提供out of vocabulary的词向量

Issue - State: closed - Opened by lujiaying over 6 years ago - 3 comments

#22 - 请问Context Features中的Word + Character + Ngram是什么意思？

Issue - State: closed - Opened by aluminumbox over 6 years ago - 3 comments

#21 - 关于训练的原始语料

Issue - State: closed - Opened by l11x0m7 over 6 years ago - 1 comment

#20 - 用法

Issue - State: closed - Opened by cmdjzs over 6 years ago - 1 comment

#19 - 词向量文件中有重复的词

Issue - State: closed - Opened by howardlau1999 over 6 years ago - 5 comments

#18 - 中文字符向量

Issue - State: open - Opened by michael92ht over 6 years ago - 47 comments

#17 - 请问词向量文件是按照词频高低来排序的吗？

Issue - State: closed - Opened by reid3290 over 6 years ago - 1 comment

#16 - can i continue training this Embedding? how?

Issue - State: closed - Opened by liuxun666 over 6 years ago - 2 comments

#15 - 为什么ppmi.baidubaike.word文件读取的时候，每个维度的值前面都有一个"数值:"且词向量的维度远大于300。

Issue - State: closed - Opened by CXX1113 over 6 years ago - 2 comments

#14 - 词的质量有待提高

Issue - State: closed - Opened by kayzhou over 6 years ago - 1 comment

#13 - UnicodeDecodeError: 'utf-8' codec can't decode bytes in position 96-97: invalid continuation byte

Issue - State: closed - Opened by GlaDOSLI over 6 years ago - 2 comments

#12 - 解压之后还是出现列数不一致的问题

Issue - State: closed - Opened by mfxss over 6 years ago - 1 comment

#11 - 训练集Corpus Size是什么单位

Issue - State: closed - Opened by AquaskyCamus over 6 years ago - 5 comments

#10 - 请问作者用linux系统读取过这些文件吗？

Issue - State: closed - Opened by mfxss over 6 years ago - 3 comments

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