Publications

(* denotes equal contribution)

2023

  1. FiLM: Fill-in Language Models for Any-Order Generation
    Tianxiao Shen, Hao Peng, Ruoqi Shen, Yao Fu, Zaid Harchaoui, and Yejin Choi
    Preprint, 2023
  2. Generating Sequences by Learning to [Self-]Correct
    Sean Welleck*, Ximing Lu*, Peter West, Faeze Brahman, Tianxiao Shen, Daniel Khashabi, and Yejin Choi
    ICLR, 2023

2022

  1. Controlling Neural Language Generation
    Tianxiao Shen
    PhD thesis, MIT, 2022
  2. Text Style Transfer with Confounders
    Tianxiao Shen, Regina Barzilay, and Tommi Jaakkola
    Preprint, 2022
  3. Controlling Directions Orthogonal to a Classifier
    Yilun Xu, Hao He, Tianxiao Shen, and Tommi Jaakkola
    ICLR, 2022
    Spotlight

2020

  1. Blank Language Models
    Tianxiao Shen*, Victor Quach*, Regina Barzilay, and Tommi Jaakkola
    EMNLP, 2020
  2. Educating Text Autoencoders: Latent Representation Guidance via Denoising
    Tianxiao Shen, Jonas Mueller, Regina Barzilay, and Tommi Jaakkola
    ICML, 2020

2019

  1. Learning to Make Generalizable and Diverse Predictions for Retrosynthesis
    Benson Chen, Tianxiao Shen, Tommi Jaakkola, and Regina Barzilay
    Preprint, 2019
  2. Mixture Models for Diverse Machine Translation: Tricks of the Trade
    Tianxiao Shen*, Myle Ott*, Michael Auli, and Marc’Aurelio Ranzato
    ICML, 2019
    Long talk

2017

  1. Style Transfer from Non-Parallel Text by Cross-Alignment
    Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola
    NeurIPS, 2017
    Spotlight

2016

  1. Making Dependency Labeling Simple, Fast and Accurate
    Tianxiao Shen, Tao Lei, and Regina Barzilay
    NAACL, 2016