All Papers

Similar to how musicians compose albums as collections of songs, I organize my research into medleys — collections of papers joined by a common theme.

At Dartmouth, I worked on two medleys. Foray into NLP has my first NLP papers. Before that, I studied neural networks for histopathology image analysis in CP2: Computational Pathology & Colorectal Polyps. I also did an undergraduate thesis, Label Noise Reduction Without Assumptions, advised by Lorenzo Torresani.


Foray into NLP (2019-2020)

Text classification, data augmentation, and NLP for social science.

  1. EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
    Jason Wei, Kai Zou
    Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019
    [Addendum] [Github]

  2. What Are People Asking About COVID-19? A Question Classification Dataset
    Jerry Wei, Chengyu Huang, Soroush Vosoughi, Jason Wei
    Workshop on NLP for COVID-19 at ACL (NLP-COVID) 2020

  3. Mitigating Political Bias in Language Models through Reinforced Calibration
    Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu, Lili Wang, Soroush Vosoughi
    AAAI Conference on Artificial Intelligence (AAAI) 2021

  4. Text Augmentation in a Multi-Task View
    Jason Wei, Chengyu Huang, Shiqi Xu, Soroush Vosoughi
    Conference of the European Chapter of the Association for Computational Linguistics (EACL) 2021


CP2: Computational Pathology & Colorectal Polyps (2019-2020)

Neural networks for histopathology image analysis, with a focus on colorectal polyps.


Tips for writing papers.
Notes on papers I’ve read.
My research values.