David Rosenberg


2023

pdf
MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
Shiyue Zhang | Shijie Wu | Ozan Irsoy | Steven Lu | Mohit Bansal | Mark Dredze | David Rosenberg
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P – that is, minimizing the forward cross-entropy, which is equivalent to maximum likelihood estimation (MLE). We have observed that models trained in this way may “over-generalize”, in the sense that they produce non-human-like text. Moreover, we believe that reverse cross-entropy, i.e., the cross-entropy of P relative to Q, is a better reflection of how a human would evaluate text generated by a model. Hence, we propose learning with MixCE, an objective that mixes the forward and reverse cross-entropies. We evaluate models trained with this objective on synthetic data settings (where P is known) and real data, and show that the resulting models yield better generated text without complex decoding strategies.

2019

pdf bib
Proceedings of the Natural Legal Language Processing Workshop 2019
Nikolaos Aletras | Elliott Ash | Leslie Barrett | Daniel Chen | Adam Meyers | Daniel Preotiuc-Pietro | David Rosenberg | Amanda Stent
Proceedings of the Natural Legal Language Processing Workshop 2019