Global Autoregressive Models for Data-Efficient Sequence Learning
Abstract
Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an autoregressive component with a log-linear component, allowing the use of global \textit{a priori} features to compensate for lack of data. We train these models in two steps. In the first step, we obtain an \emph{unnormalized} GAM that maximizes the likelihood of the data, but is improper for fast inference or evaluation. In the second step, we use this GAM to train (by distillation) a second autoregressive model that approximates the \emph{normalized} distribution associated with the GAM, and can be used for fast inference and evaluation. Our experiments focus on language modelling under synthetic conditions and show a strong perplexity reduction of using the second autoregressive model over the standard one.
Cite
@article{arxiv.1909.07063,
title = {Global Autoregressive Models for Data-Efficient Sequence Learning},
author = {Tetiana Parshakova and Jean-Marc Andreoli and Marc Dymetman},
journal= {arXiv preprint arXiv:1909.07063},
year = {2019}
}
Comments
To appear in CONLL (The SIGNLL Conference on Computational Natural Language Learning) Hong Kong, Nov. 2019