CV

Education/PostDoc

• PostDoc in Computer Science and Technology, The Chinese University of Hong Kong, Shenzhen, 2024
• Ph.D in Computer Science and Technology, Soochow University, 2022
• M.S. in Computer Science and Technology, Soochow University, 2019

Work experience

• Summer 2018: Algorithm Engineer (Intern)
  • Microsoft
  • Responsible for the research on the more natural conversation experience with dialogue act
  • As a key member in building a dialogue process description and control prototype system
  • The system contains four dimensions of contexts based on Dialogue Interpretation Theory (DIT++), leveraging dialog act and beliefs to make the robot more natural, politer, more active, and longer memory
  • Supervisor: Yue Pan

Research Project

• Research on discourse structure analysis driven by micro and macro nuclearity (NSFC)
• Fifth participant
• Responsible for the research on the Chinese macro discourse resources construction and discourse analysis methods
• As the main member in constructing a representation schema of the Chinese macro discourse structure
• As one of the main leaders in the annotation of the Macro Chinese Discourse TreeBank (MCDTB)
• Proposed two discourse parsers based on global reverse reading and topic segmentation, according to the characteristics of Chinese macro discourse structure
• Proposed three neural models, which enhance the semantic representation of discourse units, indirectly and directly modeling discourse relations separately, to recognize implicit discourse relations

Publications

MCDTB: A Macro-level Chinese Discourse TreeBank

Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou: MCDTB: A Macro-level Chinese Discourse TreeBank. In Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018): 3493-3504.

Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading

Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, Qiaoming Zhu: Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading. In Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020): 5749-5759.

Hierarchical Macro Discourse Parsing Based on Topic Segmentation

Feng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Fang Kong: Hierarchical Macro Discourse Parsing Based on Topic Segmentation. In Proceedings of the Conference on Artificial Intelligence (AAAI 2021): 13152-13160.

Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation

Feng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, Qiaoming Zhu: Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021): 2418-2431.

Automated Chinese Essay Scoring from Multiple Traits

Yaqiong He, Feng Jiang, Xiaomin Chu, Peifeng Li: Automated Chinese Essay Scoring from Multiple Traits. In Proceedings of the 29th International Conference on Computational Linguistics (COLING 2022): 3007-3016.

Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study

Yaxin Fan, Feng Jiang, Peifeng Li, and Haizhou Li: Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024): 16998–17010.

Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark

Feng Jiang, Weihao Liu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, and Haizhou Li: Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024): 495–506.

PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator

Chuyi Kong, Yaxin Fan, Xiang Wan, Feng Jiang, and Benyou Wang: PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers): 7841–7863.

Competition

• ICSR+InnoBiz 2024
  • GRASS Social Robotic Competition Award (TOP 2)
  • This task aims to propose the use of artificial intelligence to endow better human-computer interaction, especially considering sentiment and emotions.
  • As the leader of the team (collaborate with 1 postgraduate student and 1 undergraduate).
  • Proposed a human-machine hybrid data construction method and an error-invariant data enhancement method for the no-training dataset setup.
  • Provided an end-to-end digital human framework based on LLMs for emotion perception, cognition, expression, and reflection.
• NLPCC Share Task 2023
  • Chinese Grammatical Error Correction track (TOP 3)
  • The task aims to automatically correct grammatical errors that violate language rules and convert the noisy input texts to cleaned output texts. This task focuses on correcting grammatical errors made by native Chinese speakers.
  • As the leader of the team (collaborate with 1 postgraduate student).
  • Proposed a human-machine hybrid data construction method and an error-invariant data enhancement method for the no-training dataset setup.
  • Based on our Phoenix model, we trained GrammarGPT to achieve better performance than the SOTA model, only using data of 1/1200.
• CAIL 2022 (Challenge of AI in Law)
  • Summarization track (TOP 1, First Prize)
  • The task aims to generate a summary of law-related public opinion news with an average length of 1600 words.
  • As the leader of the team (collaborate with 1 postgraduate student).
  • Proposed a two-stage (extracted-generating) judicial summary model, including a Hi-XLNET to extract the summary of long documents and a T5 model to polish the summary.

Teaching

• Operating System (National Excellent Course, Online Course) (2019)
  • Teaching Assistant
  • Tutored undergraduate students’ assignments and answered their questions.
• Python Programming (Lab) (2017)
  • Teaching Assistant
  • Assisted in solving the problems students met in the lab and tutored the students’ assignments.

Service and leadership

• Organizing Committee Member (Virtual Infrastructure Chair, VIC) for EMNLP 2023
• Senior Area Editor (SAE) for ACL ARR 2024
• Area Chair (AC) for EMNLP 2023, NAACL 2024, and ACL 2024
• Reviewer for NeurIPS 2023-2024, ACL 2019-2022, AAAI 2021-2023, and IEEE/ACM-TASLP Journal
• Professional Member of the China Computer Federation (CCF) and Chinese Information Processing Society of China (CIPS)
• Member of the Shenzhen Key Laboratory of Cross-Modal Cognitive Computing
• Speaker for the CIPS ATT “LLM Series” (Specific Domain Large Language Model Construction) - Shenzhen Station
• Instructor for the CSDN “Practical Applications of Large-Scale Language Models” Series Course (3000+ students)