AI-Accelerated News Media

My research interests lie in the realization of AI-accelerated news media. This involves creating new experiences and improving operational efficiency in all stages of news production. In particular, we focus on exploring opportunities and challenges for pre-trained models in news media.

Building and Applying Information Technology Such as Pre-trained Models

• Domain-specific pre-trained models ( Press release)
• News summarization ( Journal of Natural Language Processing)
• Entity linking system ( Journal of Natural Language Processing)
• Crossword puzzle generation ( CIKM 2023)
• Semantic shift analysis ( IC2S2 2023)
• Reading time estimation ( BigData 2022 Industrial & Government Track)

Challenges in Practice

• Quantifying memorization of LLMs
  • Survey paper ( ACL 2023 Workshop)
  • Experiments on Japanese newspaper ( INLG 2024 & ACL 2025 Workshop)
  • Monitoring time-series performance degradation ( AACL-IJCNLP 2022 & Journal of Natural Language Processing)
  • Experiments on Japanese newspaper ( INLG 2024, ACL 2025 Workshop)
• Hallucination analysis ( Journal of Natural Language Processing)
• Revisiting news recommendation ( NLDB 2025)

Reference

You can see Publications for more details.