1. A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings based on Graph Modularity Yoshinari Fujinuma, Jordan Boyd-Graber, and Michael J. Paul In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL) 2019 [pdf] [talk] [slides] [code]
  2. Zika discourse in the Americas: A multilingual topic analysis of Twitter Dasha Pruss, Yoshinari Fujinuma, Ashlynn R. Daughton, Michael J. Paul, Brad Arnot, Danielle Albers Szafir, and Jordan Boyd-Graber PLOS ONE 2019 [Abs] [pdf]


  1. Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification Mozhi Zhang, Yoshinari Fujinuma, and Jordan Boyd-Graber In ACL Workshop on Deep Learning Approaches for Low-Resource Natural Language Processing 2018


  1. Substring Frequency Features for Segmentation of Japanese Katakana Words with Unlabeled Corpora Yoshinari Fujinuma, and Alvin Grissom II In Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP) 2017 [pdf]


  1. Distant-supervised Language Model for Detecting Emotional Upsurge on Twitter Yoshinari Fujinuma, Hikaru Yokono, Pascual Martı́nez-Gómez, and Akiko Aizawa In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC) 2015 [pdf]