arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.09671cs.CLcs.AIcs.LG
收藏

数据高效神经指令遵循的预学习环境表示

Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following

University of California, Berkeley(加州大学伯克利分校)

David Gaddy, Dan Klein

摘要:

我们认为学习映射的问题,从自然语言指令的状态转换(行动),在一个数据有效的方式。我们的方法从这样一个想法中得到灵感:将语言与通过前语言观察已经形成的概念联系起来应该更容易。我们增加了一个基线的预防以下的学习者与初始环境学习阶段,使用观察的语言自由状态转换,以诱导一个合适的潜在的行动表示之前,处理预防以下的训练数据。我们表明,映射到预先学习的表示大大提高了系统的表现,其表示是从有限的教学数据单独学习。

英文摘要:

We consider the problem of learning to map from natural language instructions to state transitions (actions) in a data-efficient manner. Our method takes inspiration from the idea that it should be easier to ground language to concepts that have already been formed through pre-linguistic observation. We augment a baseline instruction-following learner with an initial environment-learning phase that uses observations of language-free state transitions to induce a suitable latent representation of actions before processing the instruction-following training data. We show that mapping to pre-learned representations substantially improves performance over systems whose representations are learned from limited instructional data alone.

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。

↑