On the Relation between the NTT Kanji data dictionary and Wikipedia

Shin Asakawa

doi:10.14875/cogpsy.2017.0_6

The 15th Conference of the Japanese Society for Cognitive Psychology

セッションID: E-06

DOI https://doi.org/10.14875/cogpsy.2017.0_6

会議情報

主催: The Japanese Society for Cognitive Psychology

口頭英語

On the Relation between the NTT Kanji data dictionary and Wikipedia

Shin Asakawa

著者情報

キーワード: word embeddings, vector space models, word2vec, t-SNE, visuallization

会議録・要旨集フリー

詳細

抄録

The NTT Kanji database (Aman and Kondo, 1999) is one of the most popular kanji datasets. However, it has been long ever since it published. The word2vec (Mikolov, et al., 2013) was proposed based on large vocabulary dataset. In spite of their popularity, any comparisons have not been tried so far. We tried to figure out differences between them in terms of several ways.

責任著者(Corresponding author)

訂正情報

J-STAGEへの登録はこちら（無料）