Instructive Dialogue Summarization with Query Aggregations

TL;DR

This paper introduces InstructDS, a dialogue summarization model trained with instructive, query-based triples to better align summaries with user interests, outperforming existing models in accuracy and generalizability.

Contribution

The paper presents a novel three-step data synthesis approach and a unified instructive training framework for dialogue summarization models.

Findings

Outperforms state-of-the-art models on four datasets.

Demonstrates higher generalizability and faithfulness.

Effective in capturing user-specific interests in summaries.

Abstract

Conventional dialogue summarization methods directly generate summaries and do not consider user's specific interests. This poses challenges in cases where the users are more focused on particular topics or aspects. With the advancement of instruction-finetuned language models, we introduce instruction-tuning to dialogues to expand the capability set of dialogue summarization models. To overcome the scarcity of instructive dialogue summarization data, we propose a three-step approach to synthesize high-quality query-based summarization triples. This process involves summary-anchored query generation, query filtering, and query-based summary generation. By training a unified model called InstructDS (Instructive Dialogue Summarization) on three summarization datasets with multi-purpose instructive triples, we expand the capability of dialogue summarization models. We evaluate our method on four datasets, including dialogue summarization and dialogue reading comprehension. Experimental results show that our approach outperforms the state-of-the-art models and even models with larger sizes. Additionally, our model exhibits higher generalizability and faithfulness, as confirmed by human subjective evaluations.