Yoshinari Fujinuma


I’m currently an applied scientist at AWS AI Labs. I earned a computer science PhD with focus on cross-lingual NLP from University of Colorado Boulder.

Fill free to ping me on Twitter, Github, or by E-mail. (E-mail is the best way to contact me.)

My CV is here.

My Erdös number is 3.


May 26, 2023 Our work on efficient dialogue state tracking titled “Diable: Efficient Dialogue State Tracking as Operations on Tables” is accepted to ACL Findings and now on arXiv! Check it out at here.
May 23, 2023 Our work on bias evaluation in multilingual models titled “Comparing Biases and the Impact of Multilingual Training across Multiple Languages” is now on arXiv. Check it out at here.
Feb 17, 2023 My first pull request to Huggingface Transformers library got merged :)

selected publications


  1. acl2022_preview.png
    Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
    Yoshinari Fujinuma, Jordan Boyd-Graber, and Katharina Kann
    In Proceedings of the Association for Computational Linguistics (ACL), 2022


  1. acl2019_preview.png
    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 Association for Computational Linguistics (ACL), 2019