Refocusing on Relevance: Personalization in NLG

TL;DR

This paper advocates for incorporating user context and relevance in natural language generation to improve personalization, emphasizing the importance of value-sensitive design to address potential ethical concerns.

Contribution

It highlights the need to shift NLG focus towards relevance and personalization, proposing relevance as a key concept and discussing ethical considerations.

Findings

Relevance enhances user-oriented NLG performance

Personalization can improve response relevance and user satisfaction

Addressing ethical challenges is crucial for personalized NLG

Abstract

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.