论文标题
通过诱导的模型稀疏性，在基础语言学习中的组成概括
Compositional Generalization in Grounded Language Learning via Induced Model Sparsity
论文作者
论文摘要
我们提供了有关诱导模型稀疏性如何有助于实现构图概括并在基础语言学习问题中提高样本效率的研究。我们考虑在网格世界环境中具有简单的语言条件导航问题，并具有分离的观察结果。我们表明，标准的神经体系结构并不总是产生组成概括。为了解决这个问题，我们设计了一个包含目标标识模块的代理，该模块鼓励在说明和对象的属性中单词之间的稀疏相关性，并将它们组合在一起以找到目标。目标识别模块的输出是值迭代网络计划者的输入。即使从少数示威活动中学习，我们的代理商在包含属性的新组合的目标上保持了高度的性能。我们检查了代理的内部表示，并在单词中的单词与环境中的属性中找到正确的对应关系。
We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We show that standard neural architectures do not always yield compositional generalization. To address this, we design an agent that contains a goal identification module that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. The output of the goal identification module is the input to a value iteration network planner. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations. We examine the internal representations of our agent and find the correct correspondences between words in its dictionary and attributes in the environment.
