視覚的単語意味の対話学習における適応的対話方策の訓練
Training an adaptive dialogue policy for interactive learning of visually grounded word meanings
人間の教師との対話を通じて視覚的に接地された単語意味を学習するマルチモーダル対話システムを構築し、対話方策の違いが学習精度・速度・教師コストに与える影響を分析した上で、分類器精度と教師コストのトレードオフを最適化する適応的対話方策を訓練した。
著者: Yanchao Yu, Arash Eshghi, Oliver Lemon
分類: cs.CL, cs.AI, cs.LG, cs.RO
原文アブストラクト
We present a multi-modal dialogue system for interactive learning of perceptually grounded word meanings from a human tutor. The system integrates an incremental, semantic parsing/generation framework - Dynamic Syntax and Type Theory with Records (DS-TTR) - with a set of visual classifiers that are learned throughout the interaction and which ground the meaning representations that it produces. We use this system in interaction with a simulated human tutor to study the effects of different dialogue policies and capabilities on the accuracy of learned meanings, learning rates, and efforts/costs to the tutor. We show that the overall performance of the learning agent is affected by (1) who takes initiative in the dialogues; (2) the ability to express/use their confidence level about visual attributes; and (3) the ability to process elliptical and incrementally constructed dialogue turns. Ultimately, we train an adaptive dialogue policy which optimises the trade-off between classifier accuracy and tutoring costs.
