nwjc2vec: Word Embedding Data Constructed from NINJAL Web Japanese Corpus
暂无分享,去创建一个
[1] Kanako Komiya,et al. On SemEval-2010 Japanese WSD Task , 2011 .
[2] Jürgen Schmidhuber,et al. Learning to forget: continual prediction with LSTM , 1999 .
[3] Jeffrey Dean,et al. Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.
[4] Kikuo Maekawa,et al. Balanced corpus of contemporary written Japanese , 2013, Language Resources and Evaluation.
[5] Masayuki Asahara,et al. Archiving and Analysing Techniques of the Ultra-Large-Scale Web-Based Corpus Project of NINJAL, Japan , 2014 .
[6] Jeffrey Dean,et al. Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.
[7] Hiroya Takamura,et al. Context Representation with Word Embeddings for WSD , 2015, PACLING.