Pre-Trained Language Models and News Media

My research interest is to explore the opportunities and challenges of pre-trained language models (PLMs) in the news media.

Challenges in Practice

• Monitoring time-series performance degradation ( AACL-IJCNLP 2022, IC2S2 2023)
• Training Data Extraction ( ACL 2023 Workshop, NAACL 2024 Workshop)

Building and Applying PLMs

• Building domain-specific PLMs ( Press release)
• PLMs for news industry:
  • Crossword puzzle generation ( CIKM 2023)
  • Editors-in-the-loop summarization ( BigData 2021 Workshop)
  • Reading time estimation ( BigData 2022 Industrial & Government Track)
  • Multilingual news similarity scoring ( NAACL 2022 Workshop)
  • Next Item Recommendation ( WSDM 2021 Workshop)

Reference

You can see Publications for the detail.