PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ghazimatin, Azin, Garmash, Ekaterina, Penha, Gustavo, Sheets, Kristen, Achenbach, Martin, Semerci, Oguz, Galvez, Remi, Tannenberg, Marcus, Mantravadi, Sahitya, Narayanan, Divya, Kalaydzhyan, Ofeliya, Cole, Douglas, Carterette, Ben, Clifton, Ann, Bennett, Paul N., Hauff, Claudia, Lalmas, Mounia
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909357797539840
author Ghazimatin, Azin
Garmash, Ekaterina
Penha, Gustavo
Sheets, Kristen
Achenbach, Martin
Semerci, Oguz
Galvez, Remi
Tannenberg, Marcus
Mantravadi, Sahitya
Narayanan, Divya
Kalaydzhyan, Ofeliya
Cole, Douglas
Carterette, Ben
Clifton, Ann
Bennett, Paul N.
Hauff, Claudia
Lalmas, Mounia
author_facet Ghazimatin, Azin
Garmash, Ekaterina
Penha, Gustavo
Sheets, Kristen
Achenbach, Martin
Semerci, Oguz
Galvez, Remi
Tannenberg, Marcus
Mantravadi, Sahitya
Narayanan, Divya
Kalaydzhyan, Ofeliya
Cole, Douglas
Carterette, Ben
Clifton, Ann
Bennett, Paul N.
Hauff, Claudia
Lalmas, Mounia
contents Listeners of long-form talk-audio content, such as podcast episodes, often find it challenging to understand the overall structure and locate relevant sections. A practical solution is to divide episodes into chapters--semantically coherent segments labeled with titles and timestamps. Since most episodes on our platform at Spotify currently lack creator-provided chapters, automating the creation of chapters is essential. Scaling the chapterization of podcast episodes presents unique challenges. First, episodes tend to be less structured than written texts, featuring spontaneous discussions with nuanced transitions. Second, the transcripts are usually lengthy, averaging about 16,000 tokens, which necessitates efficient processing that can preserve context. To address these challenges, we introduce PODTILE, a fine-tuned encoder-decoder transformer to segment conversational data. The model simultaneously generates chapter transitions and titles for the input transcript. To preserve context, each input text is augmented with global context, including the episode's title, description, and previous chapter titles. In our intrinsic evaluation, PODTILE achieved an 11% improvement in ROUGE score over the strongest baseline. Additionally, we provide insights into the practical benefits of auto-generated chapters for listeners navigating episode content. Our findings indicate that auto-generated chapters serve as a useful tool for engaging with less popular podcasts. Finally, we present empirical evidence that using chapter titles can enhance effectiveness of sparse retrieval in search tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16148
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters
Ghazimatin, Azin
Garmash, Ekaterina
Penha, Gustavo
Sheets, Kristen
Achenbach, Martin
Semerci, Oguz
Galvez, Remi
Tannenberg, Marcus
Mantravadi, Sahitya
Narayanan, Divya
Kalaydzhyan, Ofeliya
Cole, Douglas
Carterette, Ben
Clifton, Ann
Bennett, Paul N.
Hauff, Claudia
Lalmas, Mounia
Information Retrieval
Artificial Intelligence
68P20
H.3.3
Listeners of long-form talk-audio content, such as podcast episodes, often find it challenging to understand the overall structure and locate relevant sections. A practical solution is to divide episodes into chapters--semantically coherent segments labeled with titles and timestamps. Since most episodes on our platform at Spotify currently lack creator-provided chapters, automating the creation of chapters is essential. Scaling the chapterization of podcast episodes presents unique challenges. First, episodes tend to be less structured than written texts, featuring spontaneous discussions with nuanced transitions. Second, the transcripts are usually lengthy, averaging about 16,000 tokens, which necessitates efficient processing that can preserve context. To address these challenges, we introduce PODTILE, a fine-tuned encoder-decoder transformer to segment conversational data. The model simultaneously generates chapter transitions and titles for the input transcript. To preserve context, each input text is augmented with global context, including the episode's title, description, and previous chapter titles. In our intrinsic evaluation, PODTILE achieved an 11% improvement in ROUGE score over the strongest baseline. Additionally, we provide insights into the practical benefits of auto-generated chapters for listeners navigating episode content. Our findings indicate that auto-generated chapters serve as a useful tool for engaging with less popular podcasts. Finally, we present empirical evidence that using chapter titles can enhance effectiveness of sparse retrieval in search tasks.
title PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters
topic Information Retrieval
Artificial Intelligence
68P20
H.3.3
url https://arxiv.org/abs/2410.16148