About Me
I am a first year CS PhD student at Center of Language and Speech Processing, Johns Hopkins University, advised by prof. Philipp Koehn. Previously, I obtained BS/MS degree at Johns Hopkins University as well. Go Hop!
My research interest lies in representation learning for language and speech. Specifically, I am curious about:
- How to better learn and utilize representation in low-resource scenarios
- How to align representation from different modalities such as jointly representing speech and text
- How to efficiently compress/segment representation for tasks that require long-context window or continuous streams
Publication
- Weiting Tan, Kevin Heffernan, Holger Schwenk, and Philipp Koehn. (2023). Multilingual Representation Distillation with Contrastive Learning. In Proceedings of EACL 2023
- Lingfeng Shen*, Weiting Tan*, Boyuan Zheng, and Daniel Khashabi. (2023). Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency. In Findings of EMNLP 2023
- Haoran Xu, Weiting Tan, Shuyue Stella Li, Yunmo Chen, Benjamin Van Durme, Philipp Koehn, and Kenton Murray. (2023). Condensing Multilingual Knowledge with Lightweight Language-Specific Module. In Proceedings of EMNLP 2023
- Weiting Tan, Chu-Cheng Lin, and Jason Eisner (2023). Structure-Aware Path Inference for Neural Finite State Transducers. To Appear at ICBINB workshop of NeurIPS 2023
- Weiting Tan, Shuoyang Ding, Huda Khayrallah, and Philipp Koehn. (2022). Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation. In Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas 2022
Manuscripts
- Weiting Tan, Eunah Cho, Ziyan Jiang, Tony Chen, Zhengyang Zhao, Gustavo Aguilar, Xing Fan, Wei Shen, and Chenlei Guo (2023). ConvoEval: A Discerning Conversational Response Evaluator Using Large Language Models. In submission to EACL 2024
- Lingfeng Shen, Boyuan Zheng, Haoran Xu, Weiting Tan, Yunmo Chen, Philipp Koehn, and Daniel Khashabi (2023) TECO: Text Evaluation via Closest Paraphrase. In submission to EACL 2024
- Weiting Tan, Haoran Xu, Lingfeng Shen, Shuyue Stella Li, Kenton Murray, Philipp Koehn, Benjamin Van Durme, and Yunmo Chen (2023). Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles. In submission to NAACL 2024
- Weiting Tan and Philipp Koehn. (2022). Bitext Mining via Contrastive Learning. arXiv abs/2208.11194
Teaching
- EN.601.465 Natural Language Processing (Course Assistant) - Fall 2022
- EN.601.421 Objected-Oriented Software Engineering (Head Course Assistant) - Spring 2021, Fall 2021
- EN.601.280 Full-stack JavaScript (Head Course Assistant) - Fall 2020
- EN.601.226 Data Structures (Course Assistant) - Fall 2019, Spring 2020
Service
- Program Chair of The First Workshop on Personalized Generative AI @CIKM'23
- Student Representative of the CS Curriculum Committee at Johns Hopkins University