Prof. Pascale FUNG, Chair Professor of Electronic and Computer Engineering and Director of Center for Artificial Intelligence Research, and her team members were recognized with two awards for their papers on early ChatGPT benchmarking and Indonesian language NLP resource respectively at the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2023). The event was hosted in Bali, Indonesia on November 1–4.

The paper, titled “NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages”, won the Resource Award. The work was cited for its innovative approach to high-quality corpus creation for low-resource Indonesian languages. Covering 12 unique dialects, the benchmark is distinguished by its manual construction which ensures top-tier quality. The work was also commended for its versatile application across diverse NLP tasks and notable emphasis on underrepresented languages.

The other paper on “A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity”, received the Area Chair Award (Language Modeling and Analysis). The paper presented a comprehensive evaluation of ChatGPT on a wide variety of tasks, and provided an extensive discussion on both the strengths and weaknesses of ChatGPT, including an appendix of over 30 pages.

Earlier in May, Prof. Fung and her students’ efforts on promoting Indonesian language NLP had been recognized with an Outstanding Paper Award at the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023). The winning paper, titled “NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages”, developed the first-ever parallel resource for 10 low-resource languages in Indonesia.