arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.02447cs.CLcs.AI
收藏

通过互动学习语言游戏

Learning Language Games through Interaction

Stanford University(斯坦福大学)

Sida I. Wang, Percy Liang, Christopher D. Manning

摘要:

我们介绍了一种新的语言学习设置相关的建设自适应自然语言接口。它的灵感来自维特根斯坦的语言游戏:一个人希望完成一些任务(例如,实现块的特定配置),但是只能与执行实际动作的计算机通信(例如,移除所有红色块)。计算机最初对语言一无所知,因此必须通过交互从头开始学习,而人类则适应计算机的能力。我们在一个积木世界中创建了一个游戏,并收集了100名参与者的互动。首先,我们分析了人类的策略,表明使用组合性和避免同义词与任务绩效呈正相关。其次,我们比较计算机策略,展示如何快速从头开始学习语义解析模型,以及建模语用学进一步加速成功玩家的学习。

英文摘要:

We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a human wishes to accomplish some task (e.g., achieving a certain configuration of blocks), but can only communicate with a computer, who performs the actual actions (e.g., removing all red blocks). The computer initially knows nothing about language and therefore must learn it from scratch through interaction, while the human adapts to the computer's capabilities. We created a game in a blocks world and collected interactions from 100 people playing it. First, we analyze the humans' strategies, showing that using compositionality and avoiding synonyms correlates positively with task performance. Second, we compare computer strategies, showing how to quickly learn a semantic parsing model from scratch, and that modeling pragmatics further accelerates learning for successful players.

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。

↑