Ni, Jingwei
Ph.D. Candidate (ETH Zurich)
M.Sc. in Data Science and Machine Learning (University College London)
B.Eng. in Computer Science (University of Hong Kong)
Bibliography
Jingwei Ni is a Ph.D. Student in the research group of Prof. Elliott Ash, co-supervised by Prof. Markus Leippold (UZH) and Prof. Mrinmaya Sachan (ETH Zurich). He completed his Bachelor's degree in Computer Science at the University of Hong Kong and his Master's degree in Data Science and Machine Learning at University College London.
Research Interests
Jingwei's research interests lie in the field of AI applications, including fact-checking, scientific communication, AI for social good; as well as interdisciplinary research in finance, economy, and social science. Additionally, he is passionate about causality and causal NLP, which is becoming increasingly important, as we are in an era where LLMs learn strong correlations instead of causation.
Publications
- external pageCHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools (with Julia Bingler, Chiara Colesanti-Senni, Mathias Kraus, Glen Gostlow, Tobias Schimanski, Dominik Stammbach, Saeid Ashraf Vaghefi, Qian Wang, Nicolas Webersinke, Tobias Wekhof, Tingyu Yu & Markus Leippold), Working Paper arXiv, October 2023
- external pageWhen Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP (with Zhijing Jin, Qian Wang, Mrinmaya Sachan & Markus Leippold), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 7465–7488 (2023)
- external pageOriginal or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance (with Zhijing Jin, Markus Freitag, Mrinmaya Sachan, and Bernhard Schoelkopf), Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 5303–5320 (2022)
- external pageCausal Direction in Data Matters: Implications of Causal and Anticausal Learning in NLP (with Zhijing Jin, Julius von Kügelgen, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, and Bernhard Schoelkopf), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 9499–9513 (2021)
- Financial Time Series Prediction Model Based Recurrent Neural Network (with Chaozhi Chen and Yachun Gao), The 17th International Computer Conference on Wavelet Active Media Technology and Information Processing, Chengdu, China (2020)