Hi π
I am a master student at Wuhan University. My current research is focusing on the natural language processing area, supervised by Prof. Fei Liγ In my research, I focus on information extraction tasks within natural language processing, particularly on enhancing cross-document information extraction models through the use of discourse information. This includes leveraging the structure and semantic information of discourse through techniques such as Rhetorical Structure Theory (RST) and lexical chains to enhance document-level representations. Additionally, I am dedicated to enriching datasets for Chinese information extraction tasks to improve model accuracy and robustness. Additionally, I am very interested in multimodal large models and MoE models. My recent work has focused on constructing anthropomorphic LLMs.
Education
- Sept. 2018 - Jun. 2022 B.S., East China University of Science and Technology
- Sept. 2022 - Jun. 2025 M.S., Wuhan University
Publications
- Qiang Gao, Bobo Li, Zixiang Meng, Yunlong Li, Jun Zhou, Fei Li, Chong Teng, and Donghong Ji. 2024. Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5907β5921, Torino, Italia. ELRA and ICCL.
- Gao, Qiang, Zixiang Meng, Bobo Li, Jun Zhou, Fei Li, Chong Teng, and Donghong Ji. Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm. arXiv preprint arXiv:2406.16021 (2024). (ACL2024 Findings)
- Zixiang Meng, Qiang Gao, Di Guo, Yunlong Li, Bobo Li, Hao Fei, Shengqiong Wu, Fei Li, Chong Teng, and Donghong Ji. 2024. MMLSCU: A Dataset for Multi-modal Multi-domain Live Streaming Comment Understanding. In Proceedings of the ACM on Web Conference 2024 (WWW β24). Association for Computing Machinery, New York, NY, USA, 4395β4406. https://doi.org/10.1145/3589334.3645677
- Xiaqiang Tang, Qiang Gao(co-author), Jian Li, Nan Du, Qi Li, Sihong Xie. MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity COLING2025.
