# Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats

arXiv: https://arxiv.org/abs/2211.14954 · HTML: https://mlsanity.com/paper/2211.14954/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 27 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [Unsupervised Topic Segmentation of Meetings with BERT Embeddings](https://mlsanity.com/paper/2106.12978/) (2021)

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

- [From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://mlsanity.com/paper/2402.17633/) (2024)
- [PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters](https://mlsanity.com/paper/2410.16148/) (2024)
- [Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation](https://mlsanity.com/paper/2601.02128/) (2026)
- [Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features](https://mlsanity.com/paper/2602.06647/) (2026)
- [Linear Semantic Segmentation for Low-Resource Spoken Dialects](https://mlsanity.com/paper/2605.06276/) (2026)

## Abstract (arXiv)

Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic segmentation often focus on segmentation of structured texts. In this paper, we comprehensively analyze the generalization capabilities of state-of-the-art topic segmentation models on unstructured texts. We find that: (a) Current strategies of pre-training on a large corpus of structured text such as Wiki-727K do not help in transferability to unstructured texts. (b) Training from scratch with only a relatively small-sized dataset of the target unstructured domain improves the segmentation results by a significant margin.