Sangwoo Cho

About Me

Hello! (안녕하세요!)

I am a senior research scientist at Tencent AI Lab. My research focuses on the areas of summarization, long document understanding, and understanding of LLMs. I am also interested in multi-modal Audio and Vision with Large Language models.

Are you a self-motivated student seeking an enriching internship experience? Please reach out to me via email to explore exciting internship opportunities throughout the year. Our internships not only offer valuable hands-on research experience but also provide opportunities for publishing papers.

📝 CV

Research Interests

• LLM, Multi-modal LLM, summarization, long document understanding

Publications

• SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization
  Sangwoo Cho, Kaiqiang Song, Chao Zhao, Xiaoyang Wang, Dong Yu
  arXiv.
  [PDF]

• Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention
  Kaiqiang Song∗, Xiaoyang Wang∗, Sangwoo Cho∗, Xiaoman Pan, Dong Yu
  arXiv.
  [PDF] [Code]

• Generating User-Engaging News Headlines
  Pengshan Cai, Kaiqiang Song, Sangwoo Cho, Hongwei Wang, Xiaoyang Wang, Hong Yu, Fei Liu, Dong Yu
  Association for Computational Linguistics. ACL 2023.
  [PDF] [Code]

• OASum: Large-Scale Open Domain Aspect-based Summarization
  Xianjun Yang, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Xiaoman Pan, Linda Petzold, Dong Yu
  Association for Computational Linguistics. ACL 2023 Findings.
  [PDF] [Code]

• Analyzing Influential Factors in Human Preference Judgments via GPT-4
  Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Fei Liu
  arXiv preprint arXiv:2305.14702, 2023.
  [PDF]

• Toward Unifying Text Segmentation and Long Document Summarization
  Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Fei Liu and Dong Yu
  Empirical Methods in Natural Language Processing. EMNLP 2022.
  [PDF] [Code] Oral

• Salience Allocation as Guidance for Abstractive Summarization
  Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen and Dong Yu
  Empirical Methods in Natural Language Processing. EMNLP 2022.
  [PDF] [Code]

• StreamHover: Livestream Transcript Summarization and Annotation
  Sangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Walter Chang, Hailin Jin, Jonathan Brandt, Hassan Foroosh, Fei Liu
  Empirical Methods in Natural Language Processing. EMNLP 2021.
  [PDF] [Code]

Services

• Conference Reviewers: NAACL 2021-2024, EMNLP 2019-2023, ACL 2019-2023, AAAI 2023.