arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02742cs.CLcs.AIcs.RO
收藏

组合网络为基于语言理解的系统概括提供了可能

Compositional Networks Enable Systematic Generalization for Grounded Language Understanding

MIT(麻省理工学院)

Yen-Ling Kuo, Boris Katz, Andrei Barbu

摘要:

人类在理解新句子时非常灵活,这些句子包含了他们以前从未遇到过的概念组合。最近的研究表明,虽然深度网络在呈现新句子时可以模仿一些人类语言能力,但系统变化揭示了网络语言理解能力的局限性。我们证明,这些限制可以通过解决gSCAN数据集中的泛化挑战来克服,gSCAN数据集明确衡量了智能体能够解释基于视觉的新语言命令的能力,例如,形容词和名词的新奇配对。我们采用的关键原则是组合性:网络的组成结构应该反映它们所解决的问题域的组成结构,同时允许端到端学习其他参数。我们建立了一个通用的机制,使代理,以概括他们的语言理解组成域。至关重要的是,我们的网络具有与先前工作相同的最先进性能,同时在先前工作不具备的情况下推广其知识。我们的网络还提供了一定程度的可解释性,使用户能够检查网络的每个部分都学到了什么。强大的接地语言理解,没有戏剧性的失败,没有角落的情况下,是至关重要的建设安全和公平的机器人,我们证明了组合性可以在实现这一目标中发挥的重要作用。

英文摘要:

Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset, which explicitly measures how well an agent is able to interpret novel linguistic commands grounded in vision, e.g., novel pairings of adjectives and nouns. The key principle we employ is compositionality: that the compositional structure of networks should reflect the compositional structure of the problem domain they address, while allowing other parameters to be learned end-to-end. We build a general-purpose mechanism that enables agents to generalize their language understanding to compositional domains. Crucially, our network has the same state-of-the-art performance as prior work while generalizing its knowledge when prior work does not. Our network also provides a level of interpretability that enables users to inspect what each part of networks learns. Robust grounded language understanding without dramatic failures and without corner cases is critical to building safe and fair robots; we demonstrate the significant role that compositionality can play in achieving that goal.

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。

↑