arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.09100cs.CL
收藏

基于强化学习的词造句学习

Learning to Compose Words into Sentences with Reinforcement Learning

DeepMind

Dani Yogatama, Phil Blunsom, Chris Dyer, Edward Grefenstette, Wang Ling

摘要:

我们使用强化学习来学习树结构神经网络,以计算自然语言句子的表示。与先前的工作树结构的模型,其中的树被提供作为输入或预测使用监督显式树库注释,在这项工作中的树结构进行了优化,以提高性能的下游任务。实验证明了学习任务特定的组合顺序的好处,优于顺序编码器和递归编码器的树库注释的基础上。我们分析了诱导树,并表明,虽然他们发现了一些语言直观的结构(例如,名词短语,简单动词短语),它们不同于传统的英语句法结构。

英文摘要:

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or predicted using supervision from explicit treebank annotations, the tree structures in this work are optimized to improve performance on a downstream task. Experiments demonstrate the benefit of learning task-specific composition orders, outperforming both sequential encoders and recursive encoders based on treebank annotations. We analyze the induced trees and show that while they discover some linguistically intuitive structures (e.g., noun phrases, simple verb phrases), they are different than conventional English syntactic structures.

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。

↑