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 a new task, 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.

This study proposes augmenting dialog data with think-aloud utterances (TAUs) for modeling individual personalities in text chat by LLM. TAU is a verbalization of a speaker's thought before articulating the utterance. We expect "persona LLMs" trained with TAU-augmented data can mimic the speaker's personality trait better. We tested whether the trained persona LLMs obtain the human personality with respect to Big Five, a framework characterizing human personality traits from five aspects. The results showed that LLMs trained with TAU-augmented data more closely align to the speakers' Agreeableness and Neuroticism of Big Five than those trained with original dialog data. We also found that the quality of TAU-augmentation impacts persona LLM's performance.

Weaknesses: The main problem with the paper is the game design. In visual dialogue, i.e GuessWhich game[2], does not have access to the image. It has to build up the visual representation based on the caption and dialogue. That is why having a caption is important for the GuessWhich game (L69). While in the proposed game, since Q-Bot has constant access to the images. It just needs to ask questions such that it distinguished the one image from the other.

All reviewers agree that this submission is above the acceptance threshold and they are all agree that the idea of decoupling text generation from policy learning during RL is a compelling idea and interesting idea. I would also like to recommend acceptance with two notes: 1) the reviewers raised a number of questions which were addressed in the author response, most of which are already contained in the Supplementary material, so I would advice the authors to incorporate these points in the main manuscript 2) I see your method as a way to also deal with language drift more generally. There are a couple of recent papers looking into dealing with language drift. For example, Lee et al (2019) deal with language drift through image grounding while Lazaridou et al (2020) and Lu et al. (2020) also decouple generation and policy learning, the former through reranking of language modelling samples using the RL reward and the latter through distillation such that the RL signal is never disrupting the core language knowledge. Are any of these methods superior over the others?

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 a new task, 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. 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.

Currently, human-bot symbiosis dialog systems, e.g., pre- and after-sales in E-commerce, are ubiquitous, and the dialog routing component is essential to improve the overall efficiency, reduce human resource cost, and enhance user experience. Although most existing methods can fulfil this requirement, they can only model single-source dialog data and cannot effectively capture the underlying knowledge of relations among data and subtasks. In this paper, we investigate this important problem by thoroughly mining both the data-to-task and task-to-task knowledge among various kinds of dialog data. To achieve the above targets, we propose a Gated Mechanism enhanced Multi-task Model (G3M), specifically including a novel dialog encoder and two tailored gated mechanism modules. The proposed method can play the role of hierarchical information filtering and is non-invasive to existing dialog systems. Based on two datasets collected from real world applications, extensive experimental results demonstrate the effectiveness of our method, which achieves the state-of-the-art performance by improving 8.7\%/11.8\% on RMSE metric and 2.2\%/4.4\% on F1 metric.

The advent of multiple study on crowdsourcing for speech applications concluded crowdsourcing vendors and software infrastructure has that "although the crowd sometimes approached the level greatly helped this effort. Several providers also offer integrated of the experts, it never surpassed it" (Parent and Eskenazi filtering tools that allow users to customize different 2011)). This is exacerbated during multimodal dialog data aspects of their data collection, including target population, collections, where it becomes harder to quality-control for geographical location, demographics and sometimes usable audio-video data, due to a variety of factors including even education level and expertise. Managed crowdsourcing poor visual quality caused by variable lighting, position, providers extend these options by offering further customization or occlusions, participant or administrator error, or technical and end-to-end management of the entire data issues with the system or network (McDuff, Kaliouby, and collection operation.