arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.02518cs.CLcs.LG
收藏

基于诱导模型稀疏度的扎根语言学习中的成分泛化

Compositional Generalization in Grounded Language Learning via Induced Model Sparsity

Aalto University(阿尔托大学)

Sam Spilsbury, Alexander Ilin

摘要:

我们提供了一个研究如何诱导模型稀疏可以帮助实现组合泛化和更好的样本效率接地语言学习问题。我们考虑简单的语言条件导航问题,在网格世界环境中与解开的意见。我们表明,标准的神经架构并不总是产生组合泛化。为了解决这个问题,我们设计了一个代理,其中包含一个目标识别模块,鼓励稀疏的指令和对象的属性之间的相关性,把它们组合在一起,找到目标。目标识别模块的输出是值迭代网络规划器的输入。我们的代理在包含新的属性组合的目标上保持高水平的性能,即使在从少数演示中学习时也是如此。我们检查我们的代理的内部表示,并找到其字典中的单词和环境中的属性之间的正确对应关系。

英文摘要:

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.

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。

↑