# Inference Strategies for Machine Translation with Conditional Masking

arXiv: https://arxiv.org/abs/2010.02352 · HTML: https://mlsanity.com/paper/2010.02352/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 2 of 2)

- [Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2106.05093/) (2021)
- [Learning and Analyzing Generation Order for Undirected Sequence Models](https://mlsanity.com/paper/2112.09097/) (2021)

## Abstract (arXiv)

Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clear what the best inference strategy is. We formulate masked inference as a factorization of conditional probabilities of partial sequences, show that this does not harm performance, and investigate a number of simple heuristics motivated by this perspective. We identify a thresholding strategy that has advantages over the standard "mask-predict" algorithm, and provide analyses of its behavior on machine translation tasks.