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

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 p...

Full description

Saved in:
Bibliographic Details
Main Authors Ghosh, Reshmi, Kajal, Harjeet Singh, Kamath, Sharanya, Shrivastava, Dhuri, Basu, Samyadeep, Srinivasan, Soundararajan
Format Journal Article
LanguageEnglish
Published 27.11.2022
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2211.14954