Can we develop visually grounded dialog agents that can efficiently adapt to
new tasks without forgetting how to talk to people? Such agents could leverage
a larger variety of existing data to generalize to new tasks, minimizing
expensive data collection and annotation. In this work, we study a setting we
call "Dialog without Dialog", which requires agents to develop visually
grounded dialog models that can adapt to new tasks without language level
supervision. By factorizing intention and language, our model minimizes
linguistic drift after fine-tuning for new tasks. We present qualitative
results, automated metrics, and human studies that all show our model can adapt
to new tasks and maintain language quality. Baselines either fail to perform
well at new tasks or experience language drift, becoming unintelligible to
humans. Code has been made available at
this https URL

研究如何提高视觉对话代理的适应性，使其可以在不忘记如何与人交谈的情况下，高效地适应新任务。通过分解意图和语言，减少在新任务中语言漂移的情况，并通过定性结果、自动化指标和人类研究证明我们的模型可以适应新任务并保持语言质量。