# Segmenting Scientific Abstracts into Discourse Categories: A Deep Learning-Based Approach for Sparse Labeled Data

arXiv: https://arxiv.org/abs/2005.05414 · HTML: https://mlsanity.com/paper/2005.05414/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2020.

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

- [Cross-Domain Multi-Task Learning for Sequential Sentence Classification in Research Papers](https://mlsanity.com/paper/2102.06008/) (2021)
- [Artificial Intuition: Efficient Classification of Scientific Abstracts](https://mlsanity.com/paper/2407.06093/) (2024)
- [Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information](https://mlsanity.com/paper/2305.11553/) (2023)
- [Automated Feedback Generation for a Chemistry Database and Abstracting Exercise](https://mlsanity.com/paper/2305.18319/) (2023)
- [An Information Retrieval and Extraction Tool for Covid-19 Related Papers](https://mlsanity.com/paper/2401.16430/) (2024)

## Abstract (arXiv)

The abstract of a scientific paper distills the contents of the paper into a short paragraph. In the biomedical literature, it is customary to structure an abstract into discourse categories like BACKGROUND, OBJECTIVE, METHOD, RESULT, and CONCLUSION, but this segmentation is uncommon in other fields like computer science. Explicit categories could be helpful for more granular, that is, discourse-level search and recommendation. The sparsity of labeled data makes it challenging to construct supervised machine learning solutions for automatic discourse-level segmentation of abstracts in non-bio domains. In this paper, we address this problem using transfer learning. In particular, we define three discourse categories BACKGROUND, TECHNIQUE, OBSERVATION-for an abstract because these three categories are the most common. We train a deep neural network on structured abstracts from PubMed, then fine-tune it on a small hand-labeled corpus of computer science papers. We observe an accuracy of 75% on the test corpus. We perform an ablation study to highlight the roles of the different parts of the model. Our method appears to be a promising solution to the automatic segmentation of abstracts, where the labeled data is sparse.