60 citations · 115 across the 3 of their papers we have counts for
7 papers
Generating Sequences by Learning to Self-Correct
Sean Welleck, Ximing Lu, Peter West +4
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Langu…
Controlling Directions Orthogonal to a Classifier
Yilun Xu, Hao He, Tianxiao Shen +1
We propose to identify directions invariant to a given classifier so that these directions can be controlled in tasks such as style transfer. While orthogonal decomposition is dire…
Blank Language Models
Tianxiao Shen, Victor Quach, Regina Barzilay +1
We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks. The blanks control which part of the sequence to expand, maki…
Learning to Make Generalizable and Diverse Predictions for Retrosynthesis
Benson Chen, Tianxiao Shen, Tommi S. Jaakkola +1
We propose a new model for making generalizable and diverse retrosynthetic reaction predictions. Given a target compound, the task is to predict the likely chemical reactants to pr…
Educating Text Autoencoders: Latent Representation Guidance via Denoising
Tianxiao Shen, Jonas Mueller, Regina Barzilay +1
Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintai…
Mixture Models for Diverse Machine Translation: Tricks of the Trade
Tianxiao Shen, Myle Ott, Michael Auli +1
Mixture models trained via EM are among the simplest, most widely used and well understood latent variable models in the machine learning literature. Surprisingly, these models hav…