Controllable Neural Dialogue Summarization with Personal Named Entity Planning

TL;DR

This paper introduces a controllable neural dialogue summarization framework that uses personal named entity planning to generate coherent, factually accurate summaries tailored to different perspectives, enhancing flexibility and precision.

Contribution

It presents a novel controllable generation method incorporating personal named entity planning, improving dialogue summarization's flexibility and factual consistency.

Findings

Generates fluent, factually consistent summaries.

Supports multiple summarization perspectives.

Outperforms baselines in objective and human evaluations.

Abstract

In this paper, we propose a controllable neural generation framework that can flexibly guide dialogue summarization with personal named entity planning. The conditional sequences are modulated to decide what types of information or what perspective to focus on when forming summaries to tackle the under-constrained problem in summarization tasks. This framework supports two types of use cases: (1) Comprehensive Perspective, which is a general-purpose case with no user-preference specified, considering summary points from all conversational interlocutors and all mentioned persons; (2) Focus Perspective, positioning the summary based on a user-specified personal named entity, which could be one of the interlocutors or one of the persons mentioned in the conversation. During training, we exploit occurrence planning of personal named entities and coreference information to improve temporal coherence and to minimize hallucination in neural generation. Experimental results show that our proposed framework generates fluent and factually consistent summaries under various planning controls using both objective metrics and human evaluations.