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。

从 VQA 数据中学习视觉对话代理

Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data

Words shift in meaning for many reasons, including cultural factors like new
technologies and regular linguistic processes like subjectification.
Understanding the evolution of language and culture requires disentangling
these underlying causes. Here we show how two different distributional measures
can be used to detect two different types of semantic change. The first
measure, which has been used in many previous works, analyzes global shifts in
a word's distributional semantics, it is sensitive to changes due to regular
processes of linguistic drift, such as the semantic generalization of promise
("I promise." -> "It promised to be exciting."). The second measure, which we
develop here, focuses on local changes to a word's nearest semantic neighbors;
it is more sensitive to cultural shifts, such as the change in the meaning of
cell ("prison cell" -> "cell phone"). Comparing measurements made by these two
methods allows researchers to determine whether changes are more cultural or
linguistic in nature, a distinction that is essential for work in the digital
humanities and historical linguistics.

本文介绍了两种不同的分布式度量方法如何用于检测两种不同类型的语义变化，第一种方法分析词汇分布语义的全局转变，对语言漂移等规则过程的变化敏感，第二种方法则更敏感于文化转变，两种方法的比较可以帮助研究人员确定变化的性质是更具文化性还是更具语言学性。