Towards Abstractive Grounded Summarization of Podcast Transcripts

TL;DR

This paper introduces a novel abstractive summarization method for podcast transcripts that grounds summaries in specific transcript segments, improving factual consistency and interpretability despite speech disfluencies.

Contribution

It proposes a grounding-based abstractive summarization approach tailored for spoken language transcripts, addressing factual inaccuracies and transparency issues.

Findings

Achieves promising summarization results on a large podcast dataset.

Grounded summaries help identify and correct factual inconsistencies.

Significantly improves both automatic and human evaluation metrics.

Abstract

Podcasts have recently shown a rapid rise in popularity. Summarization of podcast transcripts is of practical benefit to both content providers and consumers. It helps consumers to quickly decide whether they will listen to the podcasts and reduces the cognitive load of content providers to write summaries. Nevertheless, podcast summarization faces significant challenges including factual inconsistencies with respect to the inputs. The problem is exacerbated by speech disfluencies and recognition errors in transcripts of spoken language. In this paper, we explore a novel abstractive summarization method to alleviate these challenges. Specifically, our approach learns to produce an abstractive summary while grounding summary segments in specific portions of the transcript to allow for full inspection of summary details. We conduct a series of analyses of the proposed approach on a large podcast dataset and show that the approach can achieve promising results. Grounded summaries bring clear benefits in locating the summary and transcript segments that contain inconsistent information, and hence significantly improve summarization quality in both automatic and human evaluation metrics.