Haiming Wu
I am a PhD student at School of Computer Science & Technology of Beijing Institute of Technology.
Currently, I am studying with Professor Dawei Song.
Contact: hm.wu.edu@gmail.com
[中文简历]
News
-
Recently, I have been deeply involved in the development of the large language model (LLM) Aquila and the evaluation system FlagEval in the Intelligent Evaluation Group at Beijing Academy of Artificial Intelligence (BAAI) in Beijing. Currently, we have open the Aquila-7B model and the FlagEval platform. For more information, please refer to the official public account article of BAAI Research Institute.
-
I, along with two members of DSGroup lab (Ao Jia and Zelin Li), participated in two academic evaluation tasks, Chinese Spelling Correction (Task 8) and Chinese Grammar Correction (Task 1), in NLPCC 2023 Share Task. We achieved excellent results, ranking 4th in Task 8 and 5th in Task 1! For more detailed information, please refer to the official links: Task Description, Task 1, Task 8.
Research Interest
- Deep Learning; Machine Learning
- Natural Language Processing; Information Retrieval
- Chinese Spelling Check; Text Classification
Working Experience
-
2023.02 – Now Beijing Academy of Artificial Intelligence (BAAI), Intelligent Evaluation Group, Algorithm Engineer (intern)
-
2021.03 – 2022.10 Huawei Technologies Co., Ltd, Algorithm Engineer (intern)
Education Experience
- 2020.09 – Now, Beijing Institute of Technology, Computer science, Doctoral Degree, Supervisor: Dawei Song.
- 2019.09 – 2020.03 Université de Montréal, Computer Science and Technology, Exchange students, Supervisor: Jian-Yun Nie.
- 2018.09 – 2019.03 Westlake University, Computer Science and Technology, Exchange students, Supervisor: Yue Zhang.
- 2017.09 – 2020.07, South China Normal University, Circuit and System, Master’s Degree, Supervisor: Yue Xue.
- 2013.09 – 2017.07, Yangtze University, Information and Computing Science, Bachelor’s Degree.
Conference/Journal Publications
- Bi-DCSpell: A Bi-directional Detector-Corrector Interactive Framework for Chinese Spelling Check. Wu, Haiming, Hanqing Zhang, Richeng Xuan, and Dawei Song. arXiv preprint arXiv:2406.01879 (2024). [PDF]
- Controllable Text Generation with Residual Memory Transformer[J]. Hanqing Zhang, Si Sun, Haiming Wu, Dawei Song. arXiv preprint arXiv:2309.16231, 2023. [PDF], [code]
- Prototype-based Prompt-Instance Interaction with Causal Intervention for Few-shot Event Detection[C]. Jingyao Tang, Lishuang Li, Hongbin Lu, Xueyang Qin, Beibei Zhang, Haiming Wu. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2024: 13269-13278. [PDF]
- Improving long-tail relation extraction via adaptive adjustment and causal inference. Tang, Jingyao, Lishuang Li, Hongbin Lu, Beibei Zhang, and Haiming Wu. Neurocomputing (2023): 126563. [PDF], [BIB]
- Semi-Supervised Sentiment Classification on E-Commerce Reviews Using Tripartite Graph and Clustering. Xin Lu, Donghong Gu, Haolan Zhang, Zhengxin Song, Qianhua Cai, Hongya Zhao, Haiming Wu. International Journal of Data Warehousing and Mining (IJDWM) 18, no. 1 (2022): 1-20. PDF, [BIB]
- Bert-Pair-Networks for Sentiment Classification. Ziwen Wang, Haiming Wu, Han Liu, Qian-Hua Cai. International Conference on Machine Learning and Cybernetics (ICMLC), pp. 273-278. IEEE, 2020. [paper], [BIB]
- Granular computing-based multi-level interactive attention networks for targeted sentiment analysis. Haihui Li, Ting Yuan, Haiming Wu, Yun Xue, Xiaohui Hu. Granular Computing 5, no. 3 (2020): 387-395. [PDF], [BIB]
- Shared-private LSTM for Multi-domain Text Classification. Haiming Wu, Yue Zhang, Xi Jin, Yun Xue and Ziwen Wang. In Proceedings of the 8th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC2019), Kunming, China, October. [PDF], [Code], [BIB]
- Composite simpson method based on differential evolution algorithm for numerical integral. Qian Li, Yongqiang Mou, Junxia Guan, Qinghua Su, Beiping Wu, Haiming Wu. 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pp. 777-781. IEEE, 2016. [BIB]