Migratable AI: Personalizing Dialog Conversations with migration context

TL;DR

This paper introduces a dataset and analysis for migratable conversational AI agents, focusing on how they adapt to new embodiments with migration context to improve dialogue continuity and user experience.

Contribution

It presents a new dataset of migration-aware dialogues and evaluates generative and retrieval models with migration context, advancing migratable AI research.

Findings

Models with migration context outperform those without in dialogue quality

Human evaluations favor migration-aware models for contextual relevance

The dataset enables future development of more adaptive migratable AI systems

Abstract

The migration of conversational AI agents across different embodiments in order to maintain the continuity of the task has been recently explored to further improve user experience. However, these migratable agents lack contextual understanding of the user information and the migrated device during the dialog conversations with the user. This opens the question of how an agent might behave when migrated into an embodiment for contextually predicting the next utterance. We collected a dataset from the dialog conversations between crowdsourced workers with the migration context involving personal and non-personal utterances in different settings (public or private) of embodiment into which the agent migrated. We trained the generative and information retrieval models on the dataset using with and without migration context and report the results of both qualitative metrics and human evaluation. We believe that the migration dataset would be useful for training future migratable AI systems.