Yang Zhao

Email: yangzhao AT ibm.com
Address: 〒103-8510, 19-21 Nihonbashi-Hakozakicho,
Chuo-Ku, Tokyo, Japan

Research Interests

(i) Large Language Models; (ii) Text Summarization (Compression) and Text Generation; (iii) Evaluation.

Community Service

Program Committee & Reviewing: COLM(2024), EACL(2024), ICLR(2024), NeurIPS(2023, 2024), ACL(2020, 2021, 2023), NUSE(2020), EMNLP(2020, 2021, 2022, 2023), NAACL(2021), ACL Rolling Review(2021, 2022)

Journal Reviewing: Computer Speech & Language (2021)

Awards

IBM Outstanding Technical Achievement Award for Large Scale Training in Language (2023.5)

Publications

Conference

Yang Zhao, Masayasu Muraoka, Issei Yoshida, Bishwaranjan Bhattacharjee, Hiroshi Kanayama. A Simple-Yet-Efficient Instruction Augmentation Method for Zero-Shot Sentiment Classification. The 31th International Conference on Computational Linguistics (COLING 2025), Abu Dhabi, UAE, January 19–24, 2025.
Hiroshi Kanayama, Yang Zhao, Ran Iwamoto, Takuya Ohko. Incorporating Syntax and Lexical Knowledge to Multilingual Sentiment Classification on Large Language Models. The 62th annual meeting of the Association for Computational Linguistics (ACL 2024 Findings), Bangkok, Thailand August 11–16, 2024.
Yang Zhao, Tetsuya Nasukawa, Masayasu Muraoka, Bishwaranjan Bhattacharjee. A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification. The 61th annual meeting of the Association for Computational Linguistics (ACL 2023 Findings), Toronto, Canada. July 9-14, 2023.
Yang Zhao, Issei Yoshida. A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability Prediction. The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2022), November 20-23, 2022, Online.
Yang Zhao, Hiroshi Kanayama, Issei Yoshida, Masayasu Muraoka, Akiko Aizawa. A Simple Yet Effective Corpus Construction Method for Chinese Sentence Compression. The 13th Language Resources and Evaluation Conference (LREC 2022), Marseille, France. June 20-25, 2022.
Vitou Phy, Yang Zhao and Akiko Aizawa. Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems. The 28th International Conference on Computational Linguistics (COLING 2020), Deceber 8-13, 2020.
Ryosuke Kohita, Akifumi Wachi, Yang Zhao, Ryuki Tachibana. Q-learning with Language Model for Edit-based Unsupervised Summarization. Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), November 16-20, 2020.
Xiaoyu Shen, Yang Zhao, Hui Su and Dietrich Klakow. Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator. Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP 2019), Hong Kong, China. November 3–7, 2019.
Yang Zhao, Xiaoyu Shen, Wei Bi, Akiko Aizawa. Unsupervised Rewriter for Multi-Sentence Compression. The 57th annual meeting of the Association for Computational Linguistics (ACL 2019), Florence, Italy. July 28 –Augest 2, 2019.
Yang Zhao, Zhiyuan Luo, Akiko Aizawa. A Language Model based Evaluator for Sentence Compression. The 56th annual meeting of the Association for Computational Linguistics (ACL 2018), Melbourne, Australia. July 15 –July 20, 2018.
Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa and Guoping Long. A Conditional Variational Framework for Dialog Generation. The 55th annual meeting of the Association for Computational Linguistics (ACL 2017), Vancouver, Canada. July 30 – August 4, 2017.

Journal

Yang Zhao, Xiaoyu Shen, Hajime Senuma, Akiko Aizawa. A comprehensive study: Sentence compression with linguistic knowledge-enhanced gated neural network. Journal of Data & Knowledge Engineering. May, 2018.