About Me

I am a fifth year computer science MS/PhD student at UMass Amherst. My research interests lie mostly in the area of natural language processing and machine learning. I am advised by Professor Mohit Iyyer, in the UMass NLP Lab. Previously I completed my bachelor degree from Trinity College.

I have done internships at Amazon AI twice (dialogue generation, pre-training language models with code) and Adobe Research (document understanding).

---

Preprints

KNN-LM Does Not Improve Open-ended Text Generation
Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella, Varun Manjunatha, Mohit Iyyer
[Paper]

Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing
Shufan Wang, Sebastien Jean, Sailik Sengupta, James Gung, Nikolaos Pappas, Yi Zhang
[Paper]

---

Publications

You can’t pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM
Andrew Drozdov, Shufan Wang, Razieh Rahimi, Andrew McCallum, Hamed Zamani, and Mohit Iyyer
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), Long Paper, 2022
[Paper]

Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding
Zhichao Yang, Shufan Wang, Bhanu Pratap Singh Rawat, Avijit Mitra, Hong Yu
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), Long Paper, 2022
[Paper]

Modeling Exemplification in Long-form Question Answering via Retrieval
Shufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, Mohit Iyyer
North American Chapter of the Association for Computational Linguistics (NAACL), Long Paper, 2022
[Paper] [Code]

Combinatorial Scientific Discovery: Finding New Concept Combinations Beyond Link Prediction
Yuchen Zeng, Yelman Khan, Shufan Wang, Veronika Thost, Tengfei Ma
The Deep Learning on Graphs for NLP Workshop (DLG4NLP), at the International Conference on Learning Representations (ICLR), 2022
[Paper]

Parametric Bootstrap for Differentially Private Confidence Intervals
Cecilia Ferrando, Shufan Wang, Daniel Sheldon
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
[Paper] [Code]

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration
Shufan Wang, Laure Thompson, and Mohit Iyyer
Conference on Empirical Methods in Natural Language Processing (EMNLP), Long Paper, 2021
[Paper] [Code]

STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation
Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng and Mohit Iyyer
Conference on Empirical Methods in Natural Language Processing (EMNLP), Long Paper, 2020
[Paper] [Code]

General-Purpose Differentially-Private Confidence Intervals
Cecilia Ferrando, Shufan Wang, Daniel Sheldon
In Theory and Practice of Differential Privacy (TPDP), Conference Paper, 2020
[Paper] [Code]

Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism
Shufan Wang, Mohit Iyyer
North American Chapter of the Association for Computational Linguistics (NAACL), Short Paper, 2019
[Paper]

Evolving Network Structure of Academic Institutions
Shufan Wang, Mariam Avagyan, and Per Sebastian Skardal
Applied Network Science 2, 1, 2017
[Paper]

---

Teaching

• Fall 2020 - COMPSCI-685 Advanced Natural Language Processing (Teaching Assistant)
• Fall 2020 - COMPSCI-585 Natural Language Processing (Teaching Assistant)
• Spring 2019 - COMPSCI-105 Computer Literacy (Teaching Assistant)
• Fall 2018 - COMPSCI-121 Introduction to Problem Solving with Computers (Teaching Assistant)

---