Profile Picture

Steven Coyne

He/him

Sendai, Miyagi, Japan

PhD Candidate at the Tohoku University NLP Lab

Research Part-time Worker at the RIKEN AIP Natural Language Understanding Team


coyne.steven@gmail.com

github.com/coynestevencharles

linkedin.com/in/steven-c-coyne

Google Scholar Profile

I am studying Natural Language Processing, particularly the intersection of NLP and education. My research topic focuses on generating constructive feedback comments on English learners' writing. Other subfields of interest include automated essay evaluation, personalized tutoring systems, and writing assistance tools.

Education

PhD, Natural Language Processing (in progress)
October 2024 - September 2027
Graduate School of Information Sciences, Tohoku University
Master of Science, Natural Language Processing
October 2022 - September 2024
Graduate School of Information Sciences, Tohoku University
Bachelor of Arts, Languages and Culture Studies
September 2008 - April 2012
School of Arts and Humanities, Stockton University

Experience

Research Part-time Worker
RIKEN AIP Natural Language Understanding Team
November 2022 - Present

Research on educational natural language processing for educational technology.
AI Engineer Intern
Rakuten Group, AI for Business Department
August 2024 - September 2024

Develop practical applications incorporating AI technologies. My project focused on writing assistance for knowledge base article creation.
Research Intern
NEC Data Science Laboratory
August 2023 - October 2023

Research and development on natural language processing, machine learning, information retrieval and data engineering.
Teaching Assistant
Tohoku University
April 2023 - August 2023

Information and Data Literacy, Spring 2023

Research

International Conferences

  • Steven Coyne. Template-guided Grammatical Error Feedback Comment Generation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pp. 94-104, May 2023.
    Links: Paper, Poster, Presentation

Domestic Conferences

  • Steven Coyne, Diana Galvan-Sosa, Camélia Guerraoui, Michael Zock, Ryan Spring, Keisuke Sakaguchi, Kentaro Inui. Toward Pedagogically-Informed Automated Writing Feedback for Language Learners. JALTCALL 2024 Poster Session, Nagoya, Japan. March May 2024.
    Links: Abstract, Poster

  • Steven Coyne, Yuyang Dong. Large Language Models as Generalizable Text-to-Table Systems. In Proceedings of the 30th Annual Conference of the Association for Natural Language Processing, Kobe, Japan. pp. 3243-3248, March 2024.
    Links: Paper, Poster

  • Steven Coyne, Diana Galvan-Sosa, Keisuke Sakaguchi, Kentaro Inui. Developing a Typology for Language Learning Feedback. In Proceedings of the 29th Annual Conference of the Association for Natural Language Processing, Okinawa, Japan, pp. 2552-2557, March 2023.
    Links: Paper, Poster

  • Diana Galvan-Sosa, Steven Coyne, Keisuke Sakaguchi, Kentaro Inui. Towards grammatically-informed feedback comments. In Proceedings of the 29th Annual Conference of the Association for Natural Language Processing, Okinawa, Japan, pp. 1339-1343, March 2023.
    Links: Paper

Preprints

  • Steven Coyne, Keisuke Sakaguchi, Diana Galvan-Sosa, Michael Zock, Kentaro Inui. Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction. arXiv preprint arXiv:2303.14342, May 2023.
    Links: Paper

Activities

Reviewer

  • Workshop on Innovative Use of NLP for Building Educational Applications (BEA): 2023, 2024