... corpus of 160 million word tokens with a vocabulary size W of 70K word types. There are 2·W types of context(columns): The first or second W are counted if theword c occurs within a window of 10 ... EACL.Honkela, T. (1997). Self-organizing maps of words for natural language processing applica-tions. Proceedings of the International ICSCSymposium on Soft Computing.Honkela, T., Pulkki, V., & ... Induction, Repre-sentation of Language and Language Learning.Turney, P. D., & Pantel, P. (2010). From frequencyto meaning: Vector space models of semantics.Journal of Artificial Intelligence...