---
title: "Paragraph Segmentation Revisited — Retkowski 2026"
description: "ASR systems usually produce a flat stream of words, which makes long transcripts of lectures, talks or videos hard to read and reuse."
authors: ["Fabian Retkowski", "Alexander Waibel"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.55/"
doi: "10.63317/3eczsids4mek"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/retkowski-2026-paragraph-segmentation-revisited-standard-task/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/retkowski-2026-paragraph-segmentation-revisited-standard-task/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/4/) / Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech

# Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech

**Authors:** [Fabian Retkowski](https://md.research.elamur.ai/free/authors/fabian-retkowski/), [Alexander Waibel](https://md.research.elamur.ai/free/authors/alexander-waibel/) · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.55/) · [PDF](https://aclanthology.org/2026.lrec-1.55.pdf) · [DOI 10.63317/3eczsids4mek](https://doi.org/10.63317/3eczsids4mek) · [OpenAlex](https://openalex.org/W7160180809)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14) · [2](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
ASR systems usually produce a flat stream of words, which makes long transcripts of lectures, talks or videos hard to read and reuse. The authors argue that paragraph segmentation is the missing structuring step for such transcripts, and that progress has been held back by the lack of standard benchmarks. They release two resources. TEDPara is built from human-annotated paragraph structure in English TED talk transcripts. YTSegPara adds synthetic paragraph labels to the YouTube-based YTSeg chapter dataset.

For LLMs, they frame paragraph insertion as constrained decoding. At each sentence boundary, the model may only output a restricted set of tokens: punctuation or a paragraph break. This means the transcript text cannot be altered, and evaluation stays aligned sentence by sentence.

They also train a compact encoder model, MiniSeg, which reaches state-of-the-art accuracy. A hierarchical extension of MiniSeg predicts chapter and paragraph boundaries jointly at little extra cost. Evaluation combines automatic metrics with human judgments. The work makes paragraph segmentation a reproducible, measurable speech post-processing task and adds fine-grained, naturalistic data to text segmentation research.

## Key points
- **TEDPara corpus.** The authors collected 6,379 TED talks published from 2006 to May 2024. After removing talks without transcripts or with only one paragraph, 5,193 remain, split 80/10/10. On average a talk has about 25.8 paragraphs and 4.4 sentences per paragraph, and 21.9% of sentence boundaries are breaks. Because of licensing, only talk IDs and download scripts are distributed.
- **Granularity compared with existing benchmarks.** TEDPara segments text far more finely than YTSeg (9.12 segments/doc) and Wiki-727K (3.48 segments/doc).
- **YTSegPara corpus.** Its paragraph labels were generated with LLaMA 3.1 70B using the constrained decoding method. Documents average 44.6 paragraphs and 4.2 sentences per paragraph. It is released under CC BY-NC-SA 4.0.
- **Models.** MiniSeg uses the all-MiniLM-L12-v2 sentence encoder with weighted cross-entropy. It is binary for TEDPara and has three classes (chapter/paragraph) for YTSegPara. LLM baselines include LLaMA 3.1-8B-Instruct fine-tuned with LoRA, with up-weighted break tokens. All LLM inference uses greedy decoding.
- **Evaluation.** Automatic metrics are P_k and Boundary Similarity, computed with segeval. A human study with 8 participants used blind A/B comparisons and 5-point Likert ratings on the TEDPara test set.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

## Cited by

Cited by

2 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 1 not yet.

- [Arabic Sentence Segmentation Across Genres and Punctuation Conditions](https://md.research.elamur.ai/free/papers/langstream-2026-elkholy-arabic-sentence-segmentation-across-genres/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{retkowski2026paragraph,
  title = {{Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech}},
  author = {Retkowski, Fabian and Waibel, Alexander},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/3eczsids4mek},
  url = {https://doi.org/10.63317/3eczsids4mek}
}
```

- [← previous ParaCLEAN: Improving Translation Quality through Systematic Parallel Data Cleaning](https://md.research.elamur.ai/free/papers/mash-2026-paraclean-improving-translation-quality-through/)
- [next → Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for Japanese Text Simplification with LLMs](https://md.research.elamur.ai/free/papers/maekawa-2026-parallel-corpus-filtering-based-semantic/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/4/)

## References

39 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Doug Beeferman, Adam Berger, and John Lafferty. 1999. Statistical Models for Text Segmentation. Machine Learning, 34(1):177–210. [find](https://scholar.google.com/scholar?q=Doug+Beeferman%2C+Adam+Berger%2C+and+John+Lafferty%2E+1999%2E+Statistical+Models+for+Text+Segmentation%2E+Machine+Learning%2C+34%281%29%3A177%E2%80%93210%2E)
2. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python, 1st edition. O’Reilly, Beijing ; Cambridge [Mass.]. OCLC: ocn301885973. [find](https://scholar.google.com/scholar?q=Steven+Bird%2C+Ewan+Klein%2C+and+Edward+Loper%2E+2009%2E+Natural+language+processing+with+Python%2C+1st+edition%2E+O%E2%80%99Reilly%2C+Beijing+%3B+Cambridge+%5BMass%2E%5D%2E+OCLC%3A+ocn301885973%2E)
3. Igor A. Bolshakov and Alexander F. Gelbukh. 2001. Text Segmentation into Paragraphs Based on Local Text Cohesion. In Text, Speech and Dialogue, 4th International Conference, TSD 2001, Zelezna Ruda, Czech Republic, September 11-13, 2001, Proceedings, volume 2166 of Lecture Notes in Computer Science,… [find](https://scholar.google.com/scholar?q=Igor+A%2E+Bolshakov+and+Alexander+F%2E+Gelbukh%2E+2001%2E+Text+Segmentation+into+Paragraphs+Based+on+Local+Text+Cohesion%2E+In+Text%2C+Speech+and+Dialogue%2C+4th+International+Conference%2C+TSD+2001%2C+Zelezna+Ruda%2C+Cz)
4. Meriem Boubdir, Edward Kim, Beyza Ermis, Sara Hooker, and Marzieh Fadaee. 2023. Elo Uncovered: Robustness and Best Practices in Language Model Evaluation. In Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 339– 352, Singapore. Association for Co… [find](https://scholar.google.com/scholar?q=Meriem+Boubdir%2C+Edward+Kim%2C+Beyza+Ermis%2C+Sara+Hooker%2C+and+Marzieh+Fadaee%2E+2023%2E+Elo+Uncovered%3A+Robustness+and+Best+Practices+in+Language+Model+Evaluation%2E+In+Proceedings+of+the+Third+Workshop+on+Natur)
5. Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios N. Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I. Jordan, Joseph E. Gonzalez, and Ion Stoica. 2024. Chatbot arena: an open platform for evaluating LLMs by human preference. In Proceedings of the 41st International Confere… [find](https://scholar.google.com/scholar?q=Wei%2DLin+Chiang%2C+Lianmin+Zheng%2C+Ying+Sheng%2C+Anastasios+N%2E+Angelopoulos%2C+Tianle+Li%2C+Dacheng+Li%2C+Banghua+Zhu%2C+Hao+Zhang%2C+Michael+I%2E+Jordan%2C+Joseph+E%2E+Gonzalez%2C+and+Ion+Stoica%2E+2024%2E+Chatbot+arena%3A+an+ope)
6. Katja Filippova and Michael Strube. 2006. Using linguistically motivated features for paragraph boundary identification. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 267–274, Sydney, Australia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Katja+Filippova+and+Michael+Strube%2E+2006%2E+Using+linguistically+motivated+features+for+paragraph+boundary+identification%2E+In+Proceedings+of+the+2006+Conference+on+Empirical+Methods+in+Natural+Language+)
7. Chris Fournier. 2013. Evaluating Text Segmentation using Boundary Edit Distance. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1702–1712, Sofia, Bulgaria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chris+Fournier%2E+2013%2E+Evaluating+Text+Segmentation+using+Boundary+Edit+Distance%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pag)
8. Markus Frohmann, Igor Sterner, Ivan Vulić, Benjamin Minixhofer, and Markus Schedl. 2024. Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation. [find](https://scholar.google.com/scholar?q=Markus+Frohmann%2C+Igor+Sterner%2C+Ivan+Vuli%C4%87%2C+Benjamin+Minixhofer%2C+and+Markus+Schedl%2E+2024%2E+Segment+Any+Text%3A+A+Universal+Approach+for+Robust%2C+Efficient+and+Adaptable+Sentence+Segmentation%2E)
9. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11908–11941, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+11908%E2%80%9311941%2C+Miami%2C+Florida%2C+USA%2E+Association+for+Computational+Linguistics%2E)
10. Saibo Geng, Martin Josifoski, Maxime Peyrard, and Robert West. 2023a. Grammar-Constrained Decoding for Structured NLP Tasks without Fine-tuning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10932–10952, Singapore. Association for Computational Ling… [find](https://scholar.google.com/scholar?q=Saibo+Geng%2C+Martin+Josifoski%2C+Maxime+Peyrard%2C+and+Robert+West%2E+2023a%2E+Grammar%2DConstrained+Decoding+for+Structured+NLP+Tasks+without+Fine%2Dtuning%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Meth)
11. Saibo Geng, Martin Josifosky, Maxime Peyrard, and Robert West. 2023b. Flexible Grammar-Based Constrained Decoding for Language Models. CoRR, abs/2305.13971. ArXiv: 2305.13971. [find](https://scholar.google.com/scholar?q=Saibo+Geng%2C+Martin+Josifosky%2C+Maxime+Peyrard%2C+and+Robert+West%2E+2023b%2E+Flexible+Grammar%2DBased+Constrained+Decoding+for+Language+Models%2E+CoRR%2C+abs%2F2305%2E13971%2E+ArXiv%3A+2305%2E13971%2E)
12. Azin Ghazimatin, Ekaterina Garmash, Gustavo Penha, Kristen Sheets, Martin Achenbach, Oguz Semerci, Remi Galvez, Marcus Tannenberg, Sahitya Mantravadi, Divya Narayanan, Ofeliya Kalaydzhyan, Douglas Cole, Ben Carterette, Ann Clifton, Paul N. Bennett, Claudia Hauff, and Mounia Lalmas. 2024. PODTILE: Fa… [find](https://scholar.google.com/scholar?q=Azin+Ghazimatin%2C+Ekaterina+Garmash%2C+Gustavo+Penha%2C+Kristen+Sheets%2C+Martin+Achenbach%2C+Oguz+Semerci%2C+Remi+Galvez%2C+Marcus+Tannenberg%2C+Sahitya+Mantravadi%2C+Divya+Narayanan%2C+Ofeliya+Kalaydzhyan%2C+Douglas+Col)
13. Iacopo Ghinassi, Lin Wang, Chris Newell, and Matthew Purver. 2024. Recent Trends in Linear Text Segmentation: A Survey. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3084–3095, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Iacopo+Ghinassi%2C+Lin+Wang%2C+Chris+Newell%2C+and+Matthew+Purver%2E+2024%2E+Recent+Trends+in+Linear+Text+Segmentation%3A+A+Survey%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+)
14. Goran Glavaš, Ananya Ganesh, and Swapna Somasundaran. 2021. Training and Domain Adaptation for Supervised Text Segmentation. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications, pages 110–116, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Goran+Glava%C5%A1%2C+Ananya+Ganesh%2C+and+Swapna+Somasundaran%2E+2021%2E+Training+and+Domain+Adaptation+for+Supervised+Text+Segmentation%2E+In+Proceedings+of+the+16th+Workshop+on+Innovative+Use+of+NLP+for+Building+E)
15. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, . . . , and Zhiyu Ma. 2024. The Llama 3 Herd of Models. ArXiv:2407.21783 [… [find](https://scholar.google.com/scholar?q=Aaron+Grattafiori%2C+Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+Abhishek+Kadian%2C+Ahmad+Al%2DDahle%2C+Aiesha+Letman%2C+Akhil+Mathur%2C+Alan+Schelten%2C+Alex+Vaughan%2C+Amy+Yang%2C+Angela+Fan%2C+Anirudh+Goyal%2C+Anth)
16. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In ICLR. Open-Review.net. [find](https://scholar.google.com/scholar?q=Edward+J%2E+Hu%2C+Yelong+Shen%2C+Phillip+Wallis%2C+Zeyuan+Allen%2DZhu%2C+Yuanzhi+Li%2C+Shean+Wang%2C+Lu+Wang%2C+and+Weizhu+Chen%2E+2022%2E+Lora%3A+Low%2Drank+adaptation+of+large+language+models%2E+In+ICLR%2E+Open%2DReview%2Enet%2E)
17. Riku Iikura, Makoto Okada, and Naoki Mori. 2021. Improving BERT with Focal Loss for Paragraph Segmentation of Novels. In Distributed Computing and Artificial Intelligence, 17th International Conference, pages 21–30, Cham. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Riku+Iikura%2C+Makoto+Okada%2C+and+Naoki+Mori%2E+2021%2E+Improving+BERT+with+Focal+Loss+for+Paragraph+Segmentation+of+Novels%2E+In+Distributed+Computing+and+Artificial+Intelligence%2C+17th+International+Conferenc)
18. Douglas A. Jones, Florian Wolf, Edward Gibson, Elliott Williams, Evelina Fedorenko, Douglas A. Reynolds, and Marc A. Zissman. 2003. Measuring the readability of automatic speech-to-text transcripts. In 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - INTERSPEECH 2003… [find](https://scholar.google.com/scholar?q=Douglas+A%2E+Jones%2C+Florian+Wolf%2C+Edward+Gibson%2C+Elliott+Williams%2C+Evelina+Fedorenko%2C+Douglas+A%2E+Reynolds%2C+and+Marc+A%2E+Zissman%2E+2003%2E+Measuring+the+readability+of+automatic+speech%2Dto%2Dtext+transcripts%2E+I)
19. Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penchev, Gaël Liu,… [find](https://scholar.google.com/scholar?q=Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+Louis+Rouillard%2C+Thomas+Mesnard%2C+Geoffrey+Cideron%2C+Je)
20. Omri Koshorek, Adir Cohen, Noam Mor, Michael Rotman, and Jonathan Berant. 2018. Text Segmentation as a Supervised Learning Task. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers),… [find](https://scholar.google.com/scholar?q=Omri+Koshorek%2C+Adir+Cohen%2C+Noam+Mor%2C+Michael+Rotman%2C+and+Jonathan+Berant%2E+2018%2E+Text+Segmentation+as+a+Supervised+Learning+Task%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+of+)
21. Catherine Lai, Mireia Farrús, and Johanna D. Moore. 2016. Automatic Paragraph Segmentation with Lexical and Prosodic Features. In Interspeech 2016, pages 1034–1038. ISSN: 2958-1796. [find](https://scholar.google.com/scholar?q=Catherine+Lai%2C+Mireia+Farr%C3%BAs%2C+and+Johanna+D%2E+Moore%2E+2016%2E+Automatic+Paragraph+Segmentation+with+Lexical+and+Prosodic+Features%2E+In+Interspeech+2016%2C+pages+1034%E2%80%931038%2E+ISSN%3A+2958%2D1796%2E)
22. Catherine Lai, Mireia Farrús, and Johanna D. Moore. 2020. Integrating lexical and prosodic features for automatic paragraph segmentation. Speech Communication, 121:44–57. [find](https://scholar.google.com/scholar?q=Catherine+Lai%2C+Mireia+Farr%C3%BAs%2C+and+Johanna+D%2E+Moore%2E+2020%2E+Integrating+lexical+and+prosodic+features+for+automatic+paragraph+segmentation%2E+Speech+Communication%2C+121%3A44%E2%80%9357%2E)
23. Michal Lukasik, Boris Dadachev, Kishore Papineni, and Gonçalo Simões. 2020. Text Segmentation by Cross Segment Attention. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4707–4716, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Michal+Lukasik%2C+Boris+Dadachev%2C+Kishore+Papineni%2C+and+Gon%C3%A7alo+Sim%C3%B5es%2E+2020%2E+Text+Segmentation+by+Cross+Segment+Attention%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language)
24. Scott Lundberg and Marco Tulio Ribeiro. 2023. The art of prompt design: Prompt boundaries and token healing. Towards Data Science (Medium). [find](https://scholar.google.com/scholar?q=Scott+Lundberg+and+Marco+Tulio+Ribeiro%2E+2023%2E+The+art+of+prompt+design%3A+Prompt+boundaries+and+token+healing%2E+Towards+Data+Science+%28Medium%29%2E)
25. Benjamin Minixhofer, Jonas Pfeiffer, and Ivan Vulić. 2023. Where’s the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7215–7235, Toronto, Canada.… [find](https://scholar.google.com/scholar?q=Benjamin+Minixhofer%2C+Jonas+Pfeiffer%2C+and+Ivan+Vuli%C4%87%2E+2023%2E+Where%E2%80%99s+the+Point%3F+Self%2DSupervised+Multilingual+Punctuation%2DAgnostic+Sentence+Segmentation%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+)
26. Aasish Pappu and Amanda Stent. 2015. Automatic formatted transcripts for videos. In Interspeech 2015, pages 2514–2518. ISSN: 2958-1796. [find](https://scholar.google.com/scholar?q=Aasish+Pappu+and+Amanda+Stent%2E+2015%2E+Automatic+formatted+transcripts+for+videos%2E+In+Interspeech+2015%2C+pages+2514%E2%80%932518%2E+ISSN%3A+2958%2D1796%2E)
27. Fabian Retkowski and Alexander Waibel. 2024. From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - Volume 1: Long Papers, St. Juli… [find](https://scholar.google.com/scholar?q=Fabian+Retkowski+and+Alexander+Waibel%2E+2024%2E+From+Text+Segmentation+to+Smart+Chaptering%3A+A+Novel+Benchmark+for+Structuring+Video+Transcriptions%2E+In+Proceedings+of+the+18th+Conference+of+the+European+C)
28. Askars Salimbajevs and Indra Ikauniece. 2017. System for Speech Transcription and Post-Editing in Microsoft Word. In Interspeech 2017, pages 825–826. ISSN: 2958-1796. [find](https://scholar.google.com/scholar?q=Askars+Salimbajevs+and+Indra+Ikauniece%2E+2017%2E+System+for+Speech+Transcription+and+Post%2DEditing+in+Microsoft+Word%2E+In+Interspeech+2017%2C+pages+825%E2%80%93826%2E+ISSN%3A+2958%2D1796%2E)
29. Maria Shugrina. 2010. Formatting Time-Aligned ASR Transcripts for Readability. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 198–206, Los Angeles, California. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Maria+Shugrina%2E+2010%2E+Formatting+Time%2DAligned+ASR+Transcripts+for+Readability%2E+In+Human+Language+Technologies%3A+The+2010+Annual+Conference+of+the+North+American+Chapter+of+the+Association+for+Computati)
30. Caroline Sporleder and Mirella Lapata. 2004. Automatic Paragraph Identification: A Study across Languages and Domains. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing , EMNLP 2004, A meeting of SIGDAT, a Special Interest Group of the ACL, held in conjunction… [find](https://scholar.google.com/scholar?q=Caroline+Sporleder+and+Mirella+Lapata%2E+2004%2E+Automatic+Paragraph+Identification%3A+A+Study+across+Languages+and+Domains%2E+In+Proceedings+of+the+2004+Conference+on+Empirical+Methods+in+Natural+Language+Pr)
31. Heather A. Stark. 1988. What do paragraph markings do? Discourse Processes, 11(3):275–303. Publisher: Routledge _eprint: https://doi.org/10.1080/01638538809544704. — [doi:10.1080/01638538809544704](https://doi.org/10.1080/01638538809544704) [↗](https://doi.org/10.1080/01638538809544704)
32. Máté Ákos Tündik, György Szaszák, Gábor Gosztolya, and András Beke. 2018. User-centric Evaluation of Automatic Punctuation in ASR Closed Captioning. In Interspeech 2018, pages 2628– 2632. ISSN: 2958-1796. [find](https://scholar.google.com/scholar?q=M%C3%A1t%C3%A9+%C3%81kos+T%C3%BCndik%2C+Gy%C3%B6rgy+Szasz%C3%A1k%2C+G%C3%A1bor+Gosztolya%2C+and+Andr%C3%A1s+Beke%2E+2018%2E+User%2Dcentric+Evaluation+of+Automatic+Punctuation+in+ASR+Closed+Captioning%2E+In+Interspeech+2018%2C+pages+2628%E2%80%93+2632%2E+ISSN%3A+2958%2D1)
33. Rachel Wicks and Matt Post. 2021. A unified approach to sentence segmentation of punctuated text in many languages. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Pa… [find](https://scholar.google.com/scholar?q=Rachel+Wicks+and+Matt+Post%2E+2021%2E+A+unified+approach+to+sentence+segmentation+of+punctuated+text+in+many+languages%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Lingu) [our card](https://md.research.elamur.ai/free/papers/acl-2021-wicks-unified-approach-sentence-segmentation-punctuated/)
34. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+Yang%2C+Jin)
35. Byunghwa Yoo and Kyung-Joong Kim. 2024. Improving paragraph segmentation using BERT with additional information from probability density function modeling of segmentation distances. Natural Language Processing Journal, 6:100061. [find](https://scholar.google.com/scholar?q=Byunghwa+Yoo+and+Kyung%2DJoong+Kim%2E+2024%2E+Improving+paragraph+segmentation+using+BERT+with+additional+information+from+probability+density+function+modeling+of+segmentation+distances%2E+Natural+Language+P)
36. Wlodek Zadrozny and Karen Jensen. 1991. Semantics of paragraphs. Comput. Linguist., 17(2):171– 209. Place: Cambridge, MA, USA Publisher: MIT Press. [find](https://scholar.google.com/scholar?q=Wlodek+Zadrozny+and+Karen+Jensen%2E+1991%2E+Semantics+of+paragraphs%2E+Comput%2E+Linguist%2E%2C+17%282%29%3A171%E2%80%93+209%2E+Place%3A+Cambridge%2C+MA%2C+USA+Publisher%3A+MIT+Press%2E)
37. Binggang Zhuo, Masaki Murata, and Qing Ma. 2023. Auxiliary Loss for BERT-Based Paragraph Segmentation. IEICE Transactions on Information and Systems, E106.D(1):58–67. 11. [find](https://scholar.google.com/scholar?q=Binggang+Zhuo%2C+Masaki+Murata%2C+and+Qing+Ma%2E+2023%2E+Auxiliary+Loss+for+BERT%2DBased+Paragraph+Segmentation%2E+IEICE+Transactions+on+Information+and+Systems%2C+E106%2ED%281%29%3A58%E2%80%9367%2E+11%2E)
38. Language Resource References Koshorek, Omri and Cohen, Adir and Mor, Noam and Rotman, Michael and Berant, Jonathan. 2018. Wiki-727K . TAD - The Center for AI & Data Science, Tel Aviv University. Distributed via GitHub. [find](https://scholar.google.com/scholar?q=Language+Resource+References+Koshorek%2C+Omri+and+Cohen%2C+Adir+and+Mor%2C+Noam+and+Rotman%2C+Michael+and+Berant%2C+Jonathan%2E+2018%2E+Wiki%2D727K+%2E+TAD+%2D+The+Center+for+AI+%26+Data+Science%2C+Tel+Aviv+University%2E+Distr)
39. Retkowski, Fabian and Waibel, Alexander. 2024. YTSeg (2024-07-25). Interactive Systems Lab, Karlsruhe Institute of Technology. Distributed via Hugging Face. PID https://doi.org/10.57967/hf/1824. License: CC-BY-NC-SA-4.0. — [doi:10.57967/hf/1824](https://doi.org/10.57967/hf/1824) [↗](https://doi.org/10.57967/hf/1824)