├── .gitignore ├── README.md ├── lib ├── bliki-core-3.0.16.jar └── wikipedia-parser-1.0-SNAPSHOT.jar ├── prepare.sh ├── project └── plugins.sbt ├── resources ├── fix_corpus.py └── gensim │ ├── convert_model.py │ ├── gensim_word2vec.py │ └── wiki2vec.sh ├── src └── main │ ├── java │ └── org │ │ └── idio │ │ └── wikipedia │ │ └── dumps │ │ ├── EnglishWikipediaPage.java │ │ └── WikipediaPage.java │ └── scala │ └── org │ └── idio │ └── wikipedia │ ├── dumps │ └── ReadableWiki.scala │ ├── redirects │ └── RedirectStore.scala │ ├── utils │ ├── Stemmer.scala │ └── Tokenizer.scala │ └── word2vec │ ├── ArticleCleaner.scala │ └── Word2VecCorpus.scala └── torrents ├── dewiki-gensim-word2vec-300-nostem-10cbow.torrent └── enwiki-gensim-word2vec-1000-nostem-10cbow.torrent /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/README.md -------------------------------------------------------------------------------- /lib/bliki-core-3.0.16.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/lib/bliki-core-3.0.16.jar -------------------------------------------------------------------------------- /lib/wikipedia-parser-1.0-SNAPSHOT.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/lib/wikipedia-parser-1.0-SNAPSHOT.jar -------------------------------------------------------------------------------- /prepare.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/prepare.sh -------------------------------------------------------------------------------- /project/plugins.sbt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/project/plugins.sbt -------------------------------------------------------------------------------- /resources/fix_corpus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/resources/fix_corpus.py -------------------------------------------------------------------------------- /resources/gensim/convert_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/resources/gensim/convert_model.py -------------------------------------------------------------------------------- /resources/gensim/gensim_word2vec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/resources/gensim/gensim_word2vec.py -------------------------------------------------------------------------------- /resources/gensim/wiki2vec.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/resources/gensim/wiki2vec.sh -------------------------------------------------------------------------------- /src/main/java/org/idio/wikipedia/dumps/EnglishWikipediaPage.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/java/org/idio/wikipedia/dumps/EnglishWikipediaPage.java -------------------------------------------------------------------------------- /src/main/java/org/idio/wikipedia/dumps/WikipediaPage.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/java/org/idio/wikipedia/dumps/WikipediaPage.java -------------------------------------------------------------------------------- /src/main/scala/org/idio/wikipedia/dumps/ReadableWiki.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/scala/org/idio/wikipedia/dumps/ReadableWiki.scala -------------------------------------------------------------------------------- /src/main/scala/org/idio/wikipedia/redirects/RedirectStore.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/scala/org/idio/wikipedia/redirects/RedirectStore.scala -------------------------------------------------------------------------------- /src/main/scala/org/idio/wikipedia/utils/Stemmer.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/scala/org/idio/wikipedia/utils/Stemmer.scala -------------------------------------------------------------------------------- /src/main/scala/org/idio/wikipedia/utils/Tokenizer.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/scala/org/idio/wikipedia/utils/Tokenizer.scala -------------------------------------------------------------------------------- /src/main/scala/org/idio/wikipedia/word2vec/ArticleCleaner.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/scala/org/idio/wikipedia/word2vec/ArticleCleaner.scala -------------------------------------------------------------------------------- /src/main/scala/org/idio/wikipedia/word2vec/Word2VecCorpus.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/src/main/scala/org/idio/wikipedia/word2vec/Word2VecCorpus.scala -------------------------------------------------------------------------------- /torrents/dewiki-gensim-word2vec-300-nostem-10cbow.torrent: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/torrents/dewiki-gensim-word2vec-300-nostem-10cbow.torrent -------------------------------------------------------------------------------- /torrents/enwiki-gensim-word2vec-1000-nostem-10cbow.torrent: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/idio/wiki2vec/HEAD/torrents/enwiki-gensim-word2vec-1000-nostem-10cbow.torrent --------------------------------------------------------------------------------