我們應用隨機平均梯度（SAG）演算法訓練條件隨機場（CRFs）。

We apply stochastic average gradient (SAG)algorithms for training conditional random fields (CRFs).

我們描述了一種利用CRF梯度中的結構來降低這種線性收斂隨機梯度方法的記憶體需求的實用方案，提出了一種顯著提高實用效能的非均勻取樣策略，並分析了非均勻取樣下的SAGA變異演算法的收斂速率。

We describe a practical implementation thatuses structure in the CRF gradient to reduce the memory requirement of thislinearly-convergent stochastic gradient method, propose a non-uniform samplingscheme that substantially improves practical performance, and analyze the rateof convergence of the SAGA variant under non-uniform sampling.

實驗結果表明，我們的方法往往顯著優於現有方法的訓練目標，在測試誤差上的效能優於最優調諧的隨機梯度方法。

Our experimental results reveal that ourmethod often significantly outperforms existing methods in terms of thetraining objective, and performs as well or better than optimally-tunedstochastic gradient methods in terms of test error.

條件隨機場（CRFs）是自然語言處理中普遍使用的一種工具。

Conditional random fields (CRFs) are aubiquitous tool in natural language processing.

它們用於詞性標註、語義角色標註、主題建模、資訊提取、淺層解析、命名實體識別，以及自然語言處理和計算機視覺等其他領域的大量應用。

They are used for part-of-speech tagging ,semantic role labeling , topic modeling , information extraction , shallowparsing , named-entity recognition , as well as a host of other applications innatural language processing and in other fields such as computer vision.

與本文相關的一個網站供參考：

原始碼下載地址：

更多精彩文章請關注微訊號：