arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.07063cs.LGcs.AIcs.CLstat.ML
收藏

数据有效序列学习的全局自回归模型

Global Autoregressive Models for Data-Efficient Sequence Learning

Stanford University(斯坦福大学);Naver Labs Europe(Naver Labs Europe(纳威尔欧洲实验室))

Tetiana Parshakova, Jean-Marc Andreoli, Marc Dymetman

摘要:

标准的自回归seq2seq模型很容易通过最大似然训练,但在小数据条件下往往显示出较差的结果。我们介绍了一类seq2seq模型,GAM(全球自回归模型),它结合了自回归分量与对数线性分量,允许使用全球\textit{a priori}功能,以弥补缺乏数据。我们分两步训练这些模型。在第一步中,我们得到一个\emph{unnormalized} GAM,最大限度地提高了数据的可能性,但不适合快速推理或评估。在第二步中,我们使用这个GAM来训练(通过蒸馏)第二个自回归模型,该模型近似于与GAM相关联的\emph{normalized}分布,并且可以用于快速推理和评估。我们的实验集中在语言建模的合成条件下,并显示出强大的困惑减少使用第二个自回归模型的标准。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑