首页> 外文会议>3rd workshop on representation learning for NLP 2018 >Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences
【24h】

Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences

机译:使用序列的递归-递归模型实时学习层次结构

获取原文
获取原文并翻译 | 示例

摘要

We propose a hierarchical model for sequential data that learns a tree on-the-fly, i.e. while reading the sequence. In the model, a recurrent network adapts its structure and reuses recurrent weights in a recursive manner. This creates adaptive skip-connections that ease the learning of long-term dependencies. The tree structure can either be inferred without supervision through reinforcement learning, or learned in a supervised manner. We provide preliminary experiments in a novel Math Expression Evaluation (MEE) task, which is explicitly crafted to have a hierarchical tree structure that can be used to study the effectiveness of our model. Additionally, we test our model in a well-known propositional logic and language modelling tasks. Experimental results show the potential of our approach.
机译:我们提出了一种用于顺序数据的分层模型,该模型可以即时(即在读取序列时)学习一棵树。在该模型中,循环网络调整其结构并以递归方式重用循环权重。这将创建自适应跳过连接,从而简化了长期依赖关系的学习。可以通过强化学习在没有监督的情况下推断出树结构,或者以监督的方式进行学习。我们在新颖的数学表达评估(MEE)任务中提供了初步实验,该任务明确设计为具有可用于研究模型有效性的分层树结构。此外,我们在著名的命题逻辑和语言建模任务中测试我们的模型。实验结果表明了我们方法的潜力。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号