Hi, I'm Kayo
Bonjour, je suis Kayo
今日は、かよと申します 
 你好,我是殷綺妤

[kajo iɴ]
she/her
kayoy🥸cs.cmu.edu
Curriculum Vitae


I am currently a research intern at DeepMind working with Chris Dyer in the Language Team. Next fall, I am starting my PhD in Computer Science at UC Berkeley with Dan Klein and Jacob Steinhardt.

I obtained my Master's in Language Technologies in 2022 from Carnegie Mellon University where I was advised by Graham Neubig and was a member of NeuLab. I received my Bachelor's degree in Mathematics & Computer Science in 2020 from École Polytechnique. Before that, I went to a bilingual high school and studied music and dance at the conservatoire.

My research interests right now are probably as difficult to pin down as my music taste. I am generally motivated by ideas that 1) improve our understanding of how things (i.e. black box models, natural languages, human cognition, the universe...) work, 2) build tools that benefit various communities and make the world more inclusive, 3) become elegant solutions for really hard research problems that will work efficiently and robustly in the long run.

I come from Akashi, Japan and grew up speaking 4 languages in Paris, France. Outside research, I enjoy playing music, martial arts, hiking, rock climbing, solo traveling, and making oddly specific spotify playlists.

  • 2022-06-06 I started my internship at DeepMind! If you're in London this summer, let's meet up :)
  • 2022-05-19 I was invited to the NLP Highlights Podcast for their episode on Including Signed Languages in NLP!
  • 2022-04-15 I will join UC Berkeley for my PhD next Fall!
  • 2021-11-05 Gave an invited talk at DeepMind on Natural Language Processing for Signed Languages
  • 2021-10-07 Gave an invited talk at University of Pittsburgh on Extending Neural Machine Translation to Dialogue and Signed Languages
  • 2021-09-23 Extremely honored to be selected as a Siebel Scholar Class of 2022!
  • 2021-09-17 Gave an invited talk at SIGTYP on Understanding, Improving and Evaluating Context Usage in Context-aware Machine Translation
  • 2021-08-26 Super happy to have 2 papers accepted to EMNLP 2021!
  • 2021-07-25 1 paper accepted to the AT4SSL workshop at MT Summit 2021!
  • 2021-07-05 Extremely thrilled to receive the Best Theme Paper award at ACL 2021!
  • 2021-05-06 Super excited to have 3 papers accepted to ACL 2021!
  • 2021-03-01 Gave an invited talk at Unbabel on Do Context-Aware Translation Models Pay the Right Attention?
  • 2020-10-18 Gave an invited talk at Computer Vision Talks on Sign Language Translation with Transformers
  • 2020-09-30 My first conference submission was accepted to COLING'2020!
  • 2020-09-21 Extremely honored to be awarded Global Winner in Computer Science at The Global Undergraduate Awards 2020!
  • 2020-08-31 Started my Master's degree at CMU LTI!
  • 2020-07-25 My undergraduate paper has been accepted to the SLRTP workshop at ECCV'20!
  • Research

    My research so far has been motivated by my goal to use NLP to break down communication barriers between people and give all language users access to technology. Here are some topics that I have worked on:

  • Model Interpretability: I am interested in understanding how current NLP models use contextual information to make decisions during language generation (arxiv'22) and using this information to guide models to process context more efficiently. I am also interested in how neural networks process language on a fundamental level and how machine intelligence compares with human cognition.

  • Context-aware Machine Translation: I am interested in when context, either on an intra-sentential (within the current sentence), inter-sentential (across multiple sentences), or extra-linguistic (e.g. social, temporal, cultural) level, is required during translation, and how to model these features in machine translation. My works examine when translation requires context and how well models perform on these translations (arxiv'21), how much context-aware models are actually using context (ACL'21), whether models are using the type of context we expect them to (ACL'21), and how to encourage models to use more/better context.

  • Sign Language Processing: I am interested in modeling signed languages from a linguistic perspective and extending existing language technologies to signed languages. I have argued the importance for the NLP community to include signed languages, both socially and scientifically, and how to get involved (ACL'21), I researched how to translate a signed language into a spoken language (ECCV'20, COLING'20), how to perform data augmentation for Sign Language Translation (MTSummit21), and how to perform coreference resolution of pronominal pointing signs (EMNLP'21).

  • In addition to the above topics, I am also curious about ML robustness and safety, vision x language, reward specification, computational linguistics, psycholinguistics, AI music, animal NLP.
    Please do not hesitate to reach out if you'd like to chat or collaborate! I am generally responsive to emails and Twitter messages, I am not as responsive as I'd like to be on LinkedIn.

    Publications


    * = equal contribution

    2022

    • Interpreting Language Models with Contrastive Explanations
      Kayo Yin and Graham Neubig.
      In submission.
      PDF

    2021

    • Signed Coreference Resolution
      Kayo Yin, Kenneth DeHaan and Malihe Alikhani.
      Conference on Empirical Methods in Natural Language Processing (EMNLP). November 2021.
      PDF Code/Data Video

    • When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection
      Aditi Chaudhary, Kayo Yin, Antonios Anastasopoulos and Graham Neubig.
      Conference on Empirical Methods in Natural Language Processing (EMNLP). November 2021.
      PDF Code/Data

    • When Does Translation Require Context? A Data-driven, Multilingual Exploration
      Kayo Yin*, Patrick Fernandes*, André F. T. Martins and Graham Neubig.
      In submission.
      PDF Code/Data

    • 🏆 Best Theme Paper Including Signed Languages in Natural Language Processing
      Kayo Yin, Amit Moryossef, Julie Hochgesang, Yoav Goldberg and Malihe Alikhani.
      Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP). August 2021.
      PDF Video

    • Do Context-Aware Translation Models Pay the Right Attention?
      Kayo Yin, Patrick Fernandes, Danish Pruthi, Aditi Chaudhary, André F. T. Martins and Graham Neubig.
      Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP). August 2021.
      PDF Code/Data Video

    • Measuring and Increasing Context Usage in Context-Aware Machine Translation
      Patrick Fernandes, Kayo Yin, Graham Neubig and André F. T. Martins.
      Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP). August 2021.
      PDF Code/Data

    • Data Augmentation for Sign Language Gloss Translation
      Amit Moryossef*, Kayo Yin*, Graham Neubig and Yoav Goldberg.
      18th Biennial Machine Translation Summit (MTSummit) 1st International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL). August 2021.
      PDF

    2020

    • Better Sign Language Translation with STMC-Transformer
      Kayo Yin and Jesse Read.
      Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020).
      PDF Code/Data

    • Attention is All You Sign: Sign Language Translation with Transformers
      Kayo Yin and Jesse Read.
      European Conference on Computer Vision (ECCV) Workshop on Sign Language Recognition, Translation and Production (SLRTP).
      PDF Code/Data Video

    Awards



    Copyright © Kayo Yin 2021-2022
    Last updated June 22 2022