@inproceedings{lee-etal-2020-discrepancy,
title = "On the Discrepancy between Density Estimation and Sequence Generation",
author = "Lee, Jason and
Tran, Dustin and
Firat, Orhan and
Cho, Kyunghyun",
booktitle = "Proceedings of the Fourth Workshop on Structured Prediction for NLP",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.spnlp-1.10",
doi = "10.18653/v1/2020.spnlp-1.10",
pages = "84--94",
abstract = "Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate sequence-to-sequence models using conditional log-likelihood on a test set. However, the goal of sequence-to-sequence generation (or structured prediction) is to find the best output y{\^{}} given an input x, and each task has its own downstream metric R that scores a model output by comparing against a set of references y*: R(y{\^{}}, y* | x). While we hope that a model that excels in density estimation also performs well on the downstream metric, the exact correlation has not been studied for sequence generation tasks. In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared. First, log-likelihood is highly correlated with BLEU when we consider models within the same family (e.g. autoregressive models, or latent variable models with the same parameterization of the prior). However, we observe no correlation between rankings of models across different families: (1) among non-autoregressive latent variable models, a flexible prior distribution is better at density estimation but gives worse generation quality than a simple prior, and (2) autoregressive models offer the best translation performance overall, while latent variable models with a normalizing flow prior give the highest held-out log-likelihood across all datasets. Therefore, we recommend using a simple prior for the latent variable non-autoregressive model when fast generation speed is desired.",
}