中英文维基百科语料上的Word2Vec实验

最近试了一下Word2Vec, GloVe 以及对应的python版本 gensim word2vec 和 python-glove，就有心在一个更大规模的语料上测试一下，自然而然维基百科的语料进入了视线。维基百科官方提供了一个很好的维基百科数据源：https://dumps.wikimedia.org，可以方便的下载多种语言多种格式的维基百科数据。此前通过gensim的玩过英文的维基百科语料并训练LSI，LDA模型来计算两个文档的相似度，所以想看看gensim有没有提供一种简便的方式来处理维基百科数据，训练word2vec模型，用于计算词语之间的语义相似度。感谢Google，在gensim的google group下，找到了一个很长的讨论帖：training word2vec on full Wikipedia ，这个帖子基本上把如何使用gensim在维基百科语料上训练word2vec模型的问题说清楚了，甚至参与讨论的gensim的作者Radim Řehůřek博士还在新的gensim版本里加了一点修正，而对于我来说，所做的工作就是做一下验证而已。虽然github上有一个wiki2vec的项目也是做得这个事，不过我更喜欢用python gensim的方式解决问题。

关于word2vec，这方面无论中英文的参考资料相当的多，英文方面既可以看官方推荐的论文，也可以看gensim作者Radim Řehůřek博士写得一些文章。而中文方面，推荐 @licstar的《Deep Learning in NLP （一）词向量和语言模型》，有道技术沙龙的《Deep Learning实战之word2vec》，@飞林沙 的《word2vec的学习思路》, falao_beiliu 的《深度学习word2vec笔记之基础篇》和《深度学习word2vec笔记之算法篇》等。

一、英文维基百科的Word2Vec测试

首先测试了英文维基百科的数据，下载的是xml压缩后的最新数据（下载日期是2015年3月1号），大概11G，下载地址：

https://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2

处理包括两个阶段，首先将xml的wiki数据转换为text格式，通过下面这个脚本(process_wiki.py)实现：

#!/usr/bin/env python# -*- coding: utf-8 -*- import loggingimport os.pathimport sys from gensim.corpora import WikiCorpus if __name__ == '__main__':    program = os.path.basename(sys.argv[0])    logger = logging.getLogger(program)     logging.basicConfig(format='%(asctime)s: %(levelname)s: %(message)s')    logging.root.setLevel(level=logging.INFO)    logger.info("running %s" % ' '.join(sys.argv))     # check and process input arguments    if len(sys.argv) < 3:        print globals()['__doc__'] % locals()        sys.exit(1)    inp, outp = sys.argv[1:3]    space = " "    i = 0     output = open(outp, 'w')    wiki = WikiCorpus(inp, lemmatize=False, dictionary={})    for text in wiki.get_texts():        output.write(space.join(text) + "\n")        i = i + 1        if (i % 10000 == 0):            logger.info("Saved " + str(i) + " articles")     output.close()    logger.info("Finished Saved " + str(i) + " articles")

这里利用了gensim里的维基百科处理类WikiCorpus，通过get_texts将维基里的每篇文章转换位1行text文本，并且去掉了标点符号等内容，注意这里“wiki = WikiCorpus(inp, lemmatize=False, dictionary={})”将lemmatize设置为False的主要目的是不使用pattern模块来进行英文单词的词干化处理，无论你的电脑是否已经安装了pattern，因为使用pattern会严重影响这个处理过程，变得很慢。

执行”python process_wiki.py enwiki-latest-pages-articles.xml.bz2 wiki.en.text”:

2015-03-07 15:08:39,181: INFO: running process_enwiki.py enwiki-latest-pages-articles.xml.bz2 wiki.en.text2015-03-07 15:11:12,860: INFO: Saved 10000 articles2015-03-07 15:13:25,369: INFO: Saved 20000 articles2015-03-07 15:15:19,771: INFO: Saved 30000 articles2015-03-07 15:16:58,424: INFO: Saved 40000 articles2015-03-07 15:18:12,374: INFO: Saved 50000 articles2015-03-07 15:19:03,213: INFO: Saved 60000 articles2015-03-07 15:19:47,656: INFO: Saved 70000 articles2015-03-07 15:20:29,135: INFO: Saved 80000 articles2015-03-07 15:22:02,365: INFO: Saved 90000 articles2015-03-07 15:23:40,141: INFO: Saved 100000 articles.....2015-03-07 19:33:16,549: INFO: Saved 3700000 articles2015-03-07 19:33:49,493: INFO: Saved 3710000 articles2015-03-07 19:34:23,442: INFO: Saved 3720000 articles2015-03-07 19:34:57,984: INFO: Saved 3730000 articles2015-03-07 19:35:31,976: INFO: Saved 3740000 articles2015-03-07 19:36:05,790: INFO: Saved 3750000 articles2015-03-07 19:36:32,392: INFO: finished iterating over Wikipedia corpus of 3758076 documents with 2018886604 positions (total 15271374 articles, 2075130438 positions before pruning articles shorter than 50 words)2015-03-07 19:36:32,394: INFO: Finished Saved 3758076 articles

在我的macpro（4核16G机器）大约跑了4个半小时，处理了375万的文章后，我们得到了一个12G的text格式的英文维基百科数据wiki.en.text，格式类似这样的：

anarchism is collection of movements and ideologies that hold the state to be undesirable unnecessary or harmful these movements advocate some form of stateless society instead often based on self governed voluntary institutions or non hierarchical free associations although anti statism is central to anarchism as political philosophy anarchism also entails rejection of and often hierarchical organisation in general as an anti dogmatic philosophy anarchism draws on many currents of thought and strategy anarchism does not offer fixed body of doctrine from single particular world view instead fluxing and flowing as philosophy there are many types and traditions of anarchism not all of which are mutually exclusive anarchist schools of thought can differ fundamentally supporting anything from extreme individualism to complete collectivism strains of anarchism have often been divided into the categories of social and individualist anarchism or similar dual classifications anarchism is usually considered radical left wing ideology and much of anarchist economics and anarchist legal philosophy reflect anti authoritarian interpretations of communism collectivism syndicalism mutualism or participatory economics etymology and terminology the term anarchism is compound word composed from the word anarchy and the suffix ism themselves derived respectively from the greek anarchy from anarchos meaning one without rulers from the privative prefix ἀν an without and archos leader ruler cf archon or arkhē authority sovereignty realm magistracy and the suffix or ismos isma from the verbal infinitive suffix…

有了这个数据后，无论用原始的word2vec binary版本还是gensim中的python word2vec版本，都可以用来训练word2vec模型，不过我们试了一下前者，发现很慢，所以还是采用google group 讨论帖中的gensim word2vec方式的训练脚本，不过做了一点修改，保留了vector text格式的输出，方便debug, 脚本train_word2vec_model.py如下：

#!/usr/bin/env python# -*- coding: utf-8 -*- import loggingimport os.pathimport sysimport multiprocessing from gensim.corpora import WikiCorpusfrom gensim.models import Word2Vecfrom gensim.models.word2vec import LineSentence if __name__ == '__main__':    program = os.path.basename(sys.argv[0])    logger = logging.getLogger(program)     logging.basicConfig(format='%(asctime)s: %(levelname)s: %(message)s')    logging.root.setLevel(level=logging.INFO)    logger.info("running %s" % ' '.join(sys.argv))     # check and process input arguments    if len(sys.argv) < 4:        print globals()['__doc__'] % locals()        sys.exit(1)    inp, outp1, outp2 = sys.argv[1:4]     model = Word2Vec(LineSentence(inp), size=400, window=5, min_count=5,            workers=multiprocessing.cpu_count())     # trim unneeded model memory = use(much) less RAM    #model.init_sims(replace=True)    model.save(outp1)    model.save_word2vec_format(outp2, binary=False)

执行 “python train_word2vec_model.py wiki.en.text wiki.en.text.model wiki.en.text.vector”:

2015-03-09 22:48:29,588: INFO: running train_word2vec_model.py wiki.en.text wiki.en.text.model wiki.en.text.vector2015-03-09 22:48:29,593: INFO: collecting all words and their counts2015-03-09 22:48:29,607: INFO: PROGRESS: at sentence #0, processed 0 words and 0 word types2015-03-09 22:48:50,686: INFO: PROGRESS: at sentence #10000, processed 29353579 words and 430650 word types2015-03-09 22:49:08,476: INFO: PROGRESS: at sentence #20000, processed 54695775 words and 610833 word types2015-03-09 22:49:22,985: INFO: PROGRESS: at sentence #30000, processed 75344844 words and 742274 word types2015-03-09 22:49:35,607: INFO: PROGRESS: at sentence #40000, processed 93430415 words and 859131 word types2015-03-09 22:49:44,125: INFO: PROGRESS: at sentence #50000, processed 106057188 words and 935606 word types2015-03-09 22:49:49,185: INFO: PROGRESS: at sentence #60000, processed 114319016 words and 952771 word types2015-03-09 22:49:53,316: INFO: PROGRESS: at sentence #70000, processed 121263134 words and 969526 word types2015-03-09 22:49:57,268: INFO: PROGRESS: at sentence #80000, processed 127773799 words and 984130 word types2015-03-09 22:50:07,593: INFO: PROGRESS: at sentence #90000, processed 142688762 words and 1062932 word types2015-03-09 22:50:19,162: INFO: PROGRESS: at sentence #100000, processed 159550824 words and 1157644 word types......2015-03-09 23:11:52,977: INFO: PROGRESS: at sentence #3700000, processed 1999452503 words and 7990138 word types2015-03-09 23:11:55,367: INFO: PROGRESS: at sentence #3710000, processed 2002777270 words and 8002903 word types2015-03-09 23:11:57,842: INFO: PROGRESS: at sentence #3720000, processed 2006213923 words and 8019620 word types2015-03-09 23:12:00,439: INFO: PROGRESS: at sentence #3730000, processed 2009762733 words and 8035408 word types2015-03-09 23:12:02,793: INFO: PROGRESS: at sentence #3740000, processed 2013066196 words and 8045218 word types2015-03-09 23:12:05,178: INFO: PROGRESS: at sentence #3750000, processed 2016363087 words and 8057784 word types2015-03-09 23:12:07,013: INFO: collected 8069236 word types from a corpus of 2018886604 words and 3758076 sentences2015-03-09 23:12:12,230: INFO: total 1969354 word types after removing those with count<52015-03-09 23:12:12,230: INFO: constructing a huffman tree from 1969354 words2015-03-09 23:14:07,415: INFO: built huffman tree with maximum node depth 292015-03-09 23:14:09,790: INFO: resetting layer weights2015-03-09 23:15:04,506: INFO: training model with 4 workers on 1969354 vocabulary and 400 features, using 'skipgram'=1 'hierarchical softmax'=1 'subsample'=0 and 'negative sampling'=02015-03-09 23:15:19,112: INFO: PROGRESS: at 0.01% words, alpha 0.02500, 19098 words/s2015-03-09 23:15:20,224: INFO: PROGRESS: at 0.03% words, alpha 0.02500, 37671 words/s2015-03-09 23:15:22,305: INFO: PROGRESS: at 0.07% words, alpha 0.02500, 75393 words/s2015-03-09 23:15:27,712: INFO: PROGRESS: at 0.08% words, alpha 0.02499, 65618 words/s2015-03-09 23:15:29,452: INFO: PROGRESS: at 0.09% words, alpha 0.02500, 70966 words/s2015-03-09 23:15:34,032: INFO: PROGRESS: at 0.11% words, alpha 0.02498, 77369 words/s2015-03-09 23:15:37,249: INFO: PROGRESS: at 0.12% words, alpha 0.02498, 74935 words/s2015-03-09 23:15:40,618: INFO: PROGRESS: at 0.14% words, alpha 0.02498, 75399 words/s2015-03-09 23:15:42,301: INFO: PROGRESS: at 0.16% words, alpha 0.02497, 86029 words/s2015-03-09 23:15:46,283: INFO: PROGRESS: at 0.17% words, alpha 0.02497, 83033 words/s2015-03-09 23:15:48,374: INFO: PROGRESS: at 0.18% words, alpha 0.02497, 83370 words/s2015-03-09 23:15:51,398: INFO: PROGRESS: at 0.19% words, alpha 0.02496, 82794 words/s2015-03-09 23:15:55,069: INFO: PROGRESS: at 0.21% words, alpha 0.02496, 83753 words/s2015-03-09 23:15:57,718: INFO: PROGRESS: at 0.23% words, alpha 0.02496, 85031 words/s2015-03-09 23:16:00,106: INFO: PROGRESS: at 0.24% words, alpha 0.02495, 86567 words/s2015-03-09 23:16:05,523: INFO: PROGRESS: at 0.26% words, alpha 0.02495, 84850 words/s2015-03-09 23:16:06,596: INFO: PROGRESS: at 0.27% words, alpha 0.02495, 87926 words/s2015-03-09 23:16:09,500: INFO: PROGRESS: at 0.29% words, alpha 0.02494, 88618 words/s2015-03-09 23:16:10,714: INFO: PROGRESS: at 0.30% words, alpha 0.02494, 91023 words/s2015-03-09 23:16:18,467: INFO: PROGRESS: at 0.32% words, alpha 0.02494, 85960 words/s2015-03-09 23:16:19,547: INFO: PROGRESS: at 0.33% words, alpha 0.02493, 89140 words/s2015-03-09 23:16:23,500: INFO: PROGRESS: at 0.36% words, alpha 0.02493, 92026 words/s2015-03-09 23:16:29,738: INFO: PROGRESS: at 0.37% words, alpha 0.02491, 88180 words/s2015-03-09 23:16:32,000: INFO: PROGRESS: at 0.40% words, alpha 0.02492, 92734 words/s2015-03-09 23:16:34,392: INFO: PROGRESS: at 0.42% words, alpha 0.02491, 93300 words/s2015-03-09 23:16:41,018: INFO: PROGRESS: at 0.43% words, alpha 0.02490, 89727 words/s.......2015-03-10 05:03:31,849: INFO: PROGRESS: at 99.20% words, alpha 0.00020, 95350 words/s2015-03-10 05:03:32,901: INFO: PROGRESS: at 99.21% words, alpha 0.00020, 95350 words/s2015-03-10 05:03:34,296: INFO: PROGRESS: at 99.21% words, alpha 0.00020, 95350 words/s2015-03-10 05:03:35,635: INFO: PROGRESS: at 99.22% words, alpha 0.00020, 95349 words/s2015-03-10 05:03:36,730: INFO: PROGRESS: at 99.22% words, alpha 0.00020, 95350 words/s2015-03-10 05:03:37,489: INFO: reached the end of input; waiting to finish 8 outstanding jobs2015-03-10 05:03:37,908: INFO: PROGRESS: at 99.23% words, alpha 0.00019, 95350 words/s2015-03-10 05:03:39,028: INFO: PROGRESS: at 99.23% words, alpha 0.00019, 95350 words/s2015-03-10 05:03:40,127: INFO: PROGRESS: at 99.24% words, alpha 0.00019, 95350 words/s2015-03-10 05:03:40,910: INFO: training on 1994415728 words took 20916.4s, 95352 words/s2015-03-10 05:03:41,058: INFO: saving Word2Vec object under wiki.en.text.model, separately None2015-03-10 05:03:41,209: INFO: not storing attribute syn0norm2015-03-10 05:03:41,209: INFO: storing numpy array 'syn0' to wiki.en.text.model.syn0.npy2015-03-10 05:04:35,199: INFO: storing numpy array 'syn1' to wiki.en.text.model.syn1.npy2015-03-10 05:11:25,400: INFO: storing 1969354x400 projection weights into wiki.en.text.vector

大约跑了7个小时，我们得到了一个gensim中默认格式的word2vec model和一个原始c版本word2vec的vector格式的模型: wiki.en.text.vector，格式如下：

1969354 400
the 0.129255 0.015725 0.049174 -0.016438 -0.018912 0.032752 0.079885 0.033669 -0.077722 -0.025709 0.012775 0.044153 0.134307 0.070499 -0.002243 0.105198 -0.016832 -0.028631 -0.124312 -0.123064 -0.116838 0.051181 -0.096058 -0.049734 0.017380 -0.101221 0.058945 0.013669 -0.012755 0.061053 0.061813 0.083655 -0.069382 -0.069868 0.066529 -0.037156 -0.072935 -0.009470 0.037412 -0.004406 0.047011 0.005033 -0.066270 -0.031815 0.023160 -0.080117 0.172918 0.065486 -0.072161 0.062875 0.019939 -0.048380 0.198152 -0.098525 0.023434 0.079439 0.045150 -0.079479 -0.051441 -0.021556 -0.024981 -0.045291 0.040284 -0.082500 0.014618 -0.071998 0.031887 0.043916 0.115783 -0.174898 0.086603 -0.023124 0.007293 -0.066576 -0.164817 -0.081223 0.058412 0.000132 0.064160 0.055848 0.029776 -0.103420 -0.007541 -0.031742 0.082533 -0.061760 -0.038961 0.001754 -0.023977 0.069616 0.095920 0.017136 0.067126 -0.111310 0.053632 0.017633 -0.003875 -0.005236 0.063151 0.039729 -0.039158 0.001415 0.021754 -0.012540 0.015070 -0.062636 -0.013605 -0.031770 0.005296 -0.078119 -0.069303 -0.080634 -0.058377 0.024398 -0.028173 0.026353 0.088662 0.018755 -0.113538 0.055538 -0.086012 -0.027708 -0.028788 0.017759 0.029293 0.047674 -0.106734 -0.134380 0.048605 -0.089583 0.029426 0.030552 0.141916 -0.022653 0.017204 -0.036059 0.061045 -0.000077 -0.076579 0.066747 0.060884 -0.072817…
…

在ipython中，我们通过gensim来加载和测试这个模型，因为这个模型大约有7G，所以加载的时间也稍长一些：

In [2]: import gensim In [3]: model = gensim.models.Word2Vec.load_word2vec_format("wiki.en.text.vector", binary=False) In [4]: model.most_similar("queen")Out[4]: [(u'princess', 0.5760838389396667), (u'hyoui', 0.5671186447143555), (u'janggyung', 0.5598698854446411), (u'king', 0.5556215047836304), (u'dollallolla', 0.5540223121643066), (u'loranella', 0.5522741079330444), (u'ramphaiphanni', 0.5310937166213989), (u'jeheon', 0.5298476219177246), (u'soheon', 0.5243583917617798), (u'coronation', 0.5217245221138)] In [5]: model.most_similar("man")Out[5]: [(u'woman', 0.7120707035064697), (u'girl', 0.58659827709198), (u'handsome', 0.5637181997299194), (u'boy', 0.5425317287445068), (u'villager', 0.5084836483001709), (u'mustachioed', 0.49287813901901245), (u'mcgucket', 0.48355430364608765), (u'spider', 0.4804879426956177), (u'policeman', 0.4780033826828003), (u'stranger', 0.4750771224498749)] In [6]: model.most_similar("woman")Out[6]: [(u'man', 0.7120705842971802), (u'girl', 0.6736541986465454), (u'prostitute', 0.5765659809112549), (u'divorcee', 0.5429972410202026), (u'person', 0.5276163816452026), (u'schoolgirl', 0.5102938413619995), (u'housewife', 0.48748138546943665), (u'lover', 0.4858251214027405), (u'handsome', 0.4773051142692566), (u'boy', 0.47445783019065857)] In [8]: model.similarity("woman", "man")Out[8]: 0.71207063453821218 In [10]: model.doesnt_match("breakfast cereal dinner lunch".split())Out[10]: 'cereal' In [11]: model.similarity("woman", "girl")Out[11]: 0.67365416785207421 In [13]: model.most_similar("frog")Out[13]: [(u'toad', 0.6868536472320557), (u'barycragus', 0.6607867479324341), (u'grylio', 0.626731276512146), (u'heckscheri', 0.6208407878875732), (u'clamitans', 0.6150864362716675), (u'coplandi', 0.612680196762085), (u'pseudacris', 0.6108512878417969), (u'litoria', 0.6084023714065552), (u'raniformis', 0.6044802665710449), (u'watjulumensis', 0.6043726205825806)]

一切ok，但是当加载gensim默认的基于numpy格式的模型时，却遇到了问题：

In [1]: import gensim  In [2]: model = gensim.models.Word2Vec.load("wiki.en.text.model") In [3]: model.most_similar("man")... RuntimeWarning: invalid value encountered in divide  self.syn0norm = (self.syn0 / sqrt((self.syn0 ** 2).sum(-1))[..., newaxis]).astype(REAL) Out[3]: [(u'ahsns', nan), (u'ny\xedl', nan), (u'indradeo', nan), (u'jaimovich', nan), (u'addlepate', nan), (u'jagello', nan), (u'festenburg', nan), (u'picatic', nan), (u'tolosanum', nan), (u'mithoo', nan)]

这也是我修改前面这个脚本的原因所在，这个脚本在训练小一些的数据，譬如前10万条text的时候没任何问题，无论原始格式还是gensim格式，但是当跑完这个英文维基百科的时候，却存在这个问题，试了一些方法解决，还没有成功，如果大家有好的建议或解决方案，欢迎提出。

二、中文维基百科的Word2Vec测试

测试完英文维基百科之后，自然想试试中文的维基百科数据，与英文处理过程相似，也分两个步骤，不过这里需要对中文维基百科数据特殊处理一下，包括繁简转换，中文分词，去除非utf-8字符等。中文数据的下载地址是：https://dumps.wikimedia.org/zhwiki/latest/zhwiki-latest-pages-articles.xml.bz2。

中文维基百科的数据比较小，整个xml的压缩文件大约才1G，相对英文数据小了很多。首先用 process_wiki.py处理这个XML压缩文件，执行：python process_wiki.py zhwiki-latest-pages-articles.xml.bz2 wiki.zh.text

2015-03-11 17:39:22,739: INFO: running process_wiki.py zhwiki-latest-pages-articles.xml.bz2 wiki.zh.text2015-03-11 17:40:08,329: INFO: Saved 10000 articles2015-03-11 17:40:45,501: INFO: Saved 20000 articles2015-03-11 17:41:23,659: INFO: Saved 30000 articles2015-03-11 17:42:01,748: INFO: Saved 40000 articles2015-03-11 17:42:33,779: INFO: Saved 50000 articles......2015-03-11 17:55:23,094: INFO: Saved 200000 articles2015-03-11 17:56:14,692: INFO: Saved 210000 articles2015-03-11 17:57:04,614: INFO: Saved 220000 articles2015-03-11 17:57:57,979: INFO: Saved 230000 articles2015-03-11 17:58:16,621: INFO: finished iterating over Wikipedia corpus of 232894 documents with 51603419 positions (total 2581444 articles, 62177405 positions before pruning articles shorter than 50 words)2015-03-11 17:58:16,622: INFO: Finished Saved 232894 articles

得到了大约23万多篇中文语料的text格式的语料:wiki.zh.text，大概750多M。不过查看之后发现，除了加杂一些英文词汇外，还有很多繁体字混迹其中，这里还是参考了 @licstar《维基百科简体中文语料的获取》中的方法，安装opencc，然后将wiki.zh.text中的繁体字转化位简体字：

opencc -i wiki.zh.text -o wiki.zh.text.jian -c zht2zhs.ini

然后就是分词处理了，这次我用基于MeCab训练的一套中文分词系统来进行中文分词，目前虽还没有达到实用的状态，但是性能和分词结果基本能达到这次的使用要求：

mecab -d ../data/ -O wakati wiki.zh.text.jian -o wiki.zh.text.jian.seg -b 10000000

注意这里data目录下是给mecab训练好的分词模型和词典文件等，详细可参考《用MeCab打造一套实用的中文分词系统》。

有了中文维基百科的分词数据，还以为就可以执行word2vec模型训练了：

python train_word2vec_model.py wiki.zh.text.jian.seg wiki.zh.text.model wiki.zh.text.vector

不过仍然遇到了问题，提示的错误是：

UnicodeDecodeError: ‘utf8’ codec can’t decode bytes in position 5394-5395: invalid continuation byte

google了一下，大致是文件中包含非utf-8字符，又用iconv处理了一下这个问题：

iconv -c -t UTF-8 < wiki.zh.text.jian.seg > wiki.zh.text.jian.seg.utf-8

这样基本上就没问题了，执行：

python train_word2vec_model.py wiki.zh.text.jian.seg.utf-8 wiki.zh.text.model wiki.zh.text.vector

2015-03-11 18:50:02,586: INFO: running train_word2vec_model.py wiki.zh.text.jian.seg.utf-8 wiki.zh.text.model wiki.zh.text.vector2015-03-11 18:50:02,592: INFO: collecting all words and their counts2015-03-11 18:50:02,592: INFO: PROGRESS: at sentence #0, processed 0 words and 0 word types2015-03-11 18:50:12,476: INFO: PROGRESS: at sentence #10000, processed 12914562 words and 254662 word types2015-03-11 18:50:20,215: INFO: PROGRESS: at sentence #20000, processed 22308801 words and 373573 word types2015-03-11 18:50:28,448: INFO: PROGRESS: at sentence #30000, processed 30724902 words and 460837 word types...2015-03-11 18:52:03,498: INFO: PROGRESS: at sentence #210000, processed 143804601 words and 1483608 word types2015-03-11 18:52:07,772: INFO: PROGRESS: at sentence #220000, processed 149352283 words and 1521199 word types2015-03-11 18:52:11,639: INFO: PROGRESS: at sentence #230000, processed 154741839 words and 1563584 word types2015-03-11 18:52:12,746: INFO: collected 1575172 word types from a corpus of 156430908 words and 232894 sentences2015-03-11 18:52:13,672: INFO: total 278291 word types after removing those with count<52015-03-11 18:52:13,673: INFO: constructing a huffman tree from 278291 words2015-03-11 18:52:29,323: INFO: built huffman tree with maximum node depth 252015-03-11 18:52:29,683: INFO: resetting layer weights2015-03-11 18:52:38,805: INFO: training model with 4 workers on 278291 vocabulary and 400 features, using 'skipgram'=1 'hierarchical softmax'=1 'subsample'=0 and 'negative sampling'=02015-03-11 18:52:49,504: INFO: PROGRESS: at 0.10% words, alpha 0.02500, 15008 words/s2015-03-11 18:52:51,935: INFO: PROGRESS: at 0.38% words, alpha 0.02500, 44434 words/s2015-03-11 18:52:54,779: INFO: PROGRESS: at 0.56% words, alpha 0.02500, 53965 words/s2015-03-11 18:52:57,240: INFO: PROGRESS: at 0.62% words, alpha 0.02491, 52116 words/s2015-03-11 18:52:58,823: INFO: PROGRESS: at 0.72% words, alpha 0.02494, 55804 words/s2015-03-11 18:53:03,649: INFO: PROGRESS: at 0.94% words, alpha 0.02486, 58277 words/s2015-03-11 18:53:07,357: INFO: PROGRESS: at 1.03% words, alpha 0.02479, 56036 words/s......2015-03-11 19:22:09,002: INFO: PROGRESS: at 98.38% words, alpha 0.00044, 85936 words/s2015-03-11 19:22:10,321: INFO: PROGRESS: at 98.50% words, alpha 0.00044, 85971 words/s2015-03-11 19:22:11,934: INFO: PROGRESS: at 98.55% words, alpha 0.00039, 85940 words/s2015-03-11 19:22:13,384: INFO: PROGRESS: at 98.65% words, alpha 0.00036, 85960 words/s2015-03-11 19:22:13,883: INFO: training on 152625573 words took 1775.1s, 85982 words/s2015-03-11 19:22:13,883: INFO: saving Word2Vec object under wiki.zh.text.model, separately None2015-03-11 19:22:13,884: INFO: not storing attribute syn0norm2015-03-11 19:22:13,884: INFO: storing numpy array 'syn0' to wiki.zh.text.model.syn0.npy2015-03-11 19:22:20,797: INFO: storing numpy array 'syn1' to wiki.zh.text.model.syn1.npy2015-03-11 19:22:40,667: INFO: storing 278291x400 projection weights into wiki.zh.text.vector

让我们看一下训练好的中文维基百科word2vec模型“wiki.zh.text.vector”的效果：

In [1]: import gensim In [2]: model = gensim.models.Word2Vec.load("wiki.zh.text.model") In [3]: model.most_similar(u"足球")Out[3]: [(u'\u8054\u8d5b', 0.6553816199302673), (u'\u7532\u7ea7', 0.6530429720878601), (u'\u7bee\u7403', 0.5967546701431274), (u'\u4ff1\u4e50\u90e8', 0.5872289538383484), (u'\u4e59\u7ea7', 0.5840631723403931), (u'\u8db3\u7403\u961f', 0.5560152530670166), (u'\u4e9a\u8db3\u8054', 0.5308005809783936), (u'allsvenskan', 0.5249762535095215), (u'\u4ee3\u8868\u961f', 0.5214947462081909), (u'\u7532\u7ec4', 0.5177896022796631)] In [4]: result = model.most_similar(u"足球") In [5]: for e in result:    print e[0], e[1]   ....:     联赛 0.65538161993甲级 0.653042972088篮球 0.596754670143俱乐部 0.587228953838乙级 0.58406317234足球队 0.556015253067亚足联 0.530800580978allsvenskan 0.52497625351代表队 0.521494746208甲组 0.51778960228 In [6]: result = model.most_similar(u"男人") In [7]: for e in result:    print e[0], e[1]   ....:     女人 0.77537125349家伙 0.617369174957妈妈 0.567102909088漂亮 0.560832381248잘했어 0.540875017643谎言 0.538448691368爸爸 0.53660941124傻瓜 0.535608053207예쁘다 0.535151124001mc刘 0.529670000076 In [8]: result = model.most_similar(u"女人") In [9]: for e in result:    print e[0], e[1]   ....:     男人 0.77537125349我的某 0.589010596275妈妈 0.576344847679잘했어 0.562340974808美丽 0.555426716805爸爸 0.543958246708新娘 0.543640494347谎言 0.540272831917妞儿 0.531066179276老婆 0.528521537781 In [10]: result = model.most_similar(u"青蛙") In [11]: for e in result:    print e[0], e[1]   ....:     老鼠 0.559612870216乌龟 0.489831030369蜥蜴 0.478990525007猫 0.46728849411鳄鱼 0.461885392666蟾蜍 0.448014199734猴子 0.436584025621白雪公主 0.434905380011蚯蚓 0.433413207531螃蟹 0.4314712286 In [12]: result = model.most_similar(u"姨夫") In [13]: for e in result:    print e[0], e[1]   ....:     堂伯 0.583935439587祖父 0.574735701084妃所生 0.569327116013内弟 0.562012672424早卒 0.558042645454曕 0.553856015205胤祯 0.553288519382陈潜 0.550716996193愔之 0.550510883331叔父 0.550032019615 In [14]: result = model.most_similar(u"衣服") In [15]: for e in result:    print e[0], e[1]   ....:     鞋子 0.686688780785穿着 0.672499775887衣物 0.67173999548大衣 0.667605519295裤子 0.662670075893内裤 0.662210345268裙子 0.659705817699西装 0.648508131504洋装 0.647238850594围裙 0.642895817757 In [16]: result = model.most_similar(u"公安局") In [17]: for e in result:    print e[0], e[1]   ....:     司法局 0.730189085007公安厅 0.634275555611公安 0.612798035145房管局 0.597343325615商业局 0.597183346748军管会 0.59476184845体育局 0.59283208847财政局 0.588721752167戒毒所 0.575558543205新闻办 0.573395550251 In [18]: result = model.most_similar(u"铁道部") In [19]: for e in result:    print e[0], e[1]   ....:     盛光祖 0.565509021282交通部 0.548688530922批复 0.546967327595刘志军 0.541010737419立项 0.517836689949报送 0.510296344757计委 0.508456230164水利部 0.503531932831国务院 0.503227233887经贸委 0.50156635046 In [20]: result = model.most_similar(u"清华大学") In [21]: for e in result:    print e[0], e[1]   ....:     北京大学 0.763922810555化学系 0.724210739136物理系 0.694550514221数学系 0.684280991554中山大学 0.677202701569复旦 0.657914161682师范大学 0.656435549259哲学系 0.654701948166生物系 0.654403865337中文系 0.653147578239 In [22]: result = model.most_similar(u"卫视") In [23]: for e in result:    print e[0], e[1]   ....:     湖南 0.676812887192中文台 0.626506924629収蔵 0.621356606483黄金档 0.582251906395cctv 0.536769032478安徽 0.536752820015非同凡响 0.534517168999唱响 0.533438682556最强音 0.532605051994金鹰 0.531676828861 In [24]: result = model.most_similar(u"习近平") In [25]: for e in result:    print e[0], e[1]   ....:     胡锦涛 0.809472680092江泽民 0.754633367062李克强 0.739740967751贾庆林 0.737033963203曾庆红 0.732847094536吴邦国 0.726941585541总书记 0.719057679176李瑞环 0.716384887695温家宝 0.711952567101王岐山 0.703570842743 In [26]: result = model.most_similar(u"林丹") In [27]: for e in result:    print e[0], e[1]   ....:     黄综翰 0.538035452366蒋燕皎 0.52646958828刘鑫 0.522252976894韩晶娜 0.516120731831王晓理 0.512289524078王适 0.508560419083杨影 0.508159279823陈跃 0.507353425026龚智超 0.503159761429李敬元 0.50262516737 In [28]: result = model.most_similar(u"语言学") In [29]: for e in result:    print e[0], e[1]   ....:     社会学 0.632598280907人类学 0.623406708241历史学 0.618442356586比较文学 0.604823827744心理学 0.600066184998人文科学 0.577783346176社会心理学 0.575571238995政治学 0.574541330338地理学 0.573896467686哲学 0.573873817921 In [30]: result = model.most_similar(u"计算机") In [31]: for e in result:    print e[0], e[1]   ....:     自动化 0.674171924591应用 0.614087462425自动化系 0.611132860184材料科学 0.607891201973集成电路 0.600370049477技术 0.597518980503电子学 0.591316461563建模 0.577238917351工程学 0.572855889797微电子 0.570086717606 In [32]: model.similarity(u"计算机", u"自动化")Out[32]: 0.67417196002404789 In [33]: model.similarity(u"女人", u"男人")Out[33]: 0.77537125129824813 In [34]: model.doesnt_match(u"早餐 晚餐 午餐 中心".split())Out[34]: u'\u4e2d\u5fc3' In [35]: print model.doesnt_match(u"早餐 晚餐 午餐 中心".split())中心

有好的也有坏的case，甚至bad case可能会更多一些，这和语料库的规模有关，还和分词器的效果有关等等，不过这个实验暂且就到这里了。至于word2vec有什么用，目前除了用来来计算词语相似度外，业界更关注的是word2vec在具体的应用任务中的效果，这个才是更有意思的东东，也欢迎大家一起探讨。

注：原创文章，转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/中英文维基百科语料上的word2vec实验

相关文章:

1. 斯坦福大学深度学习与自然语言处理第三讲：高级的词向量表示
2. 斯坦福大学深度学习与自然语言处理第二讲：词向量
3. 如何计算两个文档的相似度（二）
4. 微软：Web N-gram Services
5. Beautiful Data-统计语言模型的应用三：分词7
6. 如何计算两个文档的相似度（三）
7. 用MeCab打造一套实用的中文分词系统(二)
8. Coursera公开课笔记: 斯坦福大学机器学习第二课“单变量线性回归(Linear regression with one variable)”
9. Beautiful Data-统计语言模型的应用三：分词3
10. MIT自然语言处理第三讲：概率语言模型（第三部分）

此条目发表在 自然语言处理, 语义相似度, 语言模型 分类目录，贴了 gensim, gensim word2vec, glove, Mecab, python gensim, python glove, python word2vec, word2vec, word2vec实验, word2vec应用, word2vec模型, word2vec相似度,word2vec相似度计算, word2vec词语相似度, 中文分词, 中文繁简转换, 中文维基百科语料, 中文编码转换, 文档相似度, 深度学习, 相似度, 维基百科, 维基百科语料, 英文维基百科语料, 词语相似度, 语义相似度, 语言模型 标签。将固定链接加入收藏夹。