Comparative Personalization for Multi-document Summarization
This addresses the problem of tailoring summaries to individual user preferences in multi-document summarization, representing an incremental improvement with a novel evaluation framework.
The paper tackles personalized multi-document summarization by proposing ComPSum, a framework that compares user preferences to generate structured analyses for personalized summaries, and it outperforms strong baselines on the PerMSum dataset using the AuthorMap evaluation method.
Personalized multi-document summarization (MDS) is essential for meeting individual user preferences of writing style and content focus for summaries. In this paper, we propose that for effective personalization, it is important to identify fine-grained differences between users' preferences by comparing the given user's preferences with other users' preferences.Motivated by this, we propose ComPSum, a personalized MDS framework. It first generates a structured analysis of a user by comparing their preferences with other users' preferences. The generated structured analysis is then used to guide the generation of personalized summaries. To evaluate the performance of ComPSum, we propose AuthorMap, a fine-grained reference-free evaluation framework for personalized MDS. It evaluates the personalization of a system based on the authorship attribution between two personalized summaries generated for different users. For robust evaluation of personalized MDS, we construct PerMSum, a personalized MDS dataset in the review and news domain. We evaluate the performance of ComPSum on PerMSum using AuthorMap, showing that it outperforms strong baselines.