Dialogue Inspectional Summarization with Factual Inconsistency Awareness
This addresses the problem of factual gaps in summaries for professional dialogues like legal or medical contexts, though it is incremental as it builds on prior alignment-focused methods.
The paper tackles factual inconsistency in dialogue summarization for professional domains by proposing an end-to-end framework with auxiliary tasks, resulting in more readable summaries with accurate factual coverage and detection of missing facts.
Dialogue summarization has been extensively studied and applied, where the prior works mainly focused on exploring superior model structures to align the input dialogue and the output summary. However, for professional dialogues (e.g., legal debate and medical diagnosis), semantic/statistical alignment can hardly fill the logical/factual gap between input dialogue discourse and summary output with external knowledge. In this paper, we mainly investigate the factual inconsistency problem for Dialogue Inspectional Summarization (DIS) under non-pretraining and pretraining settings. An innovative end-to-end dialogue summary generation framework is proposed with two auxiliary tasks: Expectant Factual Aspect Regularization (EFAR) and Missing Factual Entity Discrimination (MFED). Comprehensive experiments demonstrate that the proposed model can generate a more readable summary with accurate coverage of factual aspects as well as informing the user with potential missing facts detected from the input dialogue for further human intervention.