# A Two-Phase Approach for Abstractive Podcast Summarization

arXiv: https://arxiv.org/abs/2011.08291 · HTML: https://mlsanity.com/paper/2011.08291/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [A Survey on Dialogue Summarization: Recent Advances and New Frontiers](https://mlsanity.com/paper/2107.03175/) (2021)
- [OASum: Large-Scale Open Domain Aspect-based Summarization](https://mlsanity.com/paper/2212.09233/) (2022)
- [Hierarchical Summarization for Longform Spoken Dialog](https://mlsanity.com/paper/2108.09597/) (2021)
- [Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods](https://mlsanity.com/paper/2208.13265/) (2022)
- [TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domain](https://mlsanity.com/paper/2508.13798/) (2025)

## Abstract (arXiv)

Podcast summarization is different from summarization of other data formats, such as news, patents, and scientific papers in that podcasts are often longer, conversational, colloquial, and full of sponsorship and advertising information, which imposes great challenges for existing models. In this paper, we focus on abstractive podcast summarization and propose a two-phase approach: sentence selection and seq2seq learning. Specifically, we first select important sentences from the noisy long podcast transcripts. The selection is based on sentence similarity to the reference to reduce the redundancy and the associated latent topics to preserve semantics. Then the selected sentences are fed into a pre-trained encoder-decoder framework for the summary generation. Our approach achieves promising results regarding both ROUGE-based measures and human evaluations.