Refocusing on Relevance: Personalization in NLG
This work addresses the problem of inadequate personalization in NLG for users, but it is incremental as it builds on existing ideas without introducing new methods or data.
The paper argues that current NLG systems often fail to account for user intent and context, proposing a shift toward using relevance from Information Retrieval to enhance personalization in tasks like summarization and dialogue, while also highlighting potential harms and the need for value-sensitive design.
Many NLG tasks such as summarization, dialogue response, or open domain question answering focus primarily on a source text in order to generate a target response. This standard approach falls short, however, when a user's intent or context of work is not easily recoverable based solely on that source text -- a scenario that we argue is more of the rule than the exception. In this work, we argue that NLG systems in general should place a much higher level of emphasis on making use of additional context, and suggest that relevance (as used in Information Retrieval) be thought of as a crucial tool for designing user-oriented text-generating tasks. We further discuss possible harms and hazards around such personalization, and argue that value-sensitive design represents a crucial path forward through these challenges.