!! Linux ( open-suse ) に MeCab をインストール !mecab sorce http://taku910.github.io/mecab/ !IPA dic https://osdn.jp/projects/naist-jdic/ ! Python3 ## python3 ma-janome.py # zypper install swig # pip3 install mecab-python3 # # pip3.7 install janome # pip3.7 install gensim ! インストール Mecab install 2017-02-10 git clone https://github.com/taku910/mecab.git cd mecab/mecab ./configure --enable-utf8-only --witch-charaset=utf8 --prefix=$HOME/opt make make check sudo make install cd ../mecab-ipadic ./configure --with-charset=utf8 --prefix=$HOME/opt make sudo make install cd ../mecab/python python setup.py build python setup.py install --home=$HOME/opt ---- MECAB old tar xvfz mecab-xxxxxx.tgz cd mecab-xxxxx ./configure --witch-charaset=utf8 --enable-utf8-only make install NAIST tar xvfz mecab-naist-jdic-xxxx.tgz ./configure --with-charaset=utf8 make make install ---- !コーパス https://www.rondhuit.com/download.html#ldcc https://ja.wikipedia.org/wiki/Wikipedia:%E3%83%87%E3%83%BC%E3%82%BF%E3%83%99%E3%83%BC%E3%82%B9%E3%83%80%E3%82%A6%E3%83%B3%E3%83%AD%E3%83%BC%E3%83%89 https://www.ninjal.ac.jp/database/type/corpora/ http://www.s-yata.jp/corpus/nwc2010/ngrams/ ---- ! DOC_2_DOC https://upura.hatenablog.com/entry/2017/08/02/211634#f-907cd670 [Word2Vec|https://deepage.net/bigdata/machine_learning/2016/09/02/word2vec_power_of_word_vector.html] [Doc2Vec|https://deepage.net/machine_learning/2017/01/08/doc2vec.html] ---- ! ユーザ辞書の作成 *http://ailaby.com/tweet_dict/ ツイッター *https://qiita.com/newt0/items/243b6f98a31433d2faaf *https://qiita.com/newt0/items/66cb76b1c8016e9d0339