Learning a Deep Hybrid Model for Semi-Supervised Text Classification
Learning a Deep Hybrid Model for Semi-Supervised Text Classification
复制标题
DOI：
10.18653/v1/d15-1053
复制
发表时间：
2015-09
期刊：
影响因子：
--
通讯作者：
Alexander Ororbia;C. Lee Giles;D. Reitter
中科院分区：
文献类型：
--
作者：
Alexander Ororbia;C. Lee Giles;D. Reitter
我们提出了一种新的微调算法在深度混合架构的半监督文本分类。在在线学习过程的每个增量期间，微调算法用作自上而下的机制，用于在自下而上的生成学习过程之后伪联合修改模型参数。在我们所谓的自底向上自顶向下学习算法下训练的结果模型，表现出优于各种竞争模型和在监督和无监督训练数据之间进行广泛分割训练的基线。
We present a novel fine-tuning algorithm in a deep hybrid architecture for semisupervised text classification. During each increment of the online learning process, the fine-tuning algorithm serves as a top-down mechanism for pseudo-jointly modifying model parameters following a bottom-up generative learning pass. The resulting model, trained under what we call the Bottom-Up-Top-Down learning algorithm, is shown to outperform a variety of competitive models and baselines trained across a wide range of splits between supervised and unsupervised training data.