# Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information

arXiv: https://arxiv.org/abs/2305.11553 · HTML: https://mlsanity.com/paper/2305.11553/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 18 of 18)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts](https://mlsanity.com/paper/1710.06071/) (2017)
- [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)
- [Argument Generation with Retrieval, Planning, and Realization](https://mlsanity.com/paper/1906.03717/) (2019)
- [Aspect-Controlled Neural Argument Generation](https://mlsanity.com/paper/2005.00084/) (2020)
- [Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation](https://mlsanity.com/paper/2001.00891/) (2020)
- [Unsupervised Topic Segmentation of Meetings with BERT Embeddings](https://mlsanity.com/paper/2106.12978/) (2021)
- [Toward Unifying Text Segmentation and Long Document Summarization](https://mlsanity.com/paper/2210.16422/) (2022)
- [Attention-based Neural Text Segmentation](https://mlsanity.com/paper/1808.09935/) (2018)
- [Unsupervised Extractive Summarization using Pointwise Mutual Information](https://mlsanity.com/paper/2102.06272/) (2021)
- [Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence](https://mlsanity.com/paper/2110.07160/) (2021)
- [Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learning](https://mlsanity.com/paper/1907.00962/) (2019)
- [Text Segmentation based on Semantic Word Embeddings](https://mlsanity.com/paper/1503.05543/) (2015)
- [Structural Text Segmentation of Legal Documents](https://mlsanity.com/paper/2012.03619/) (2020)
- [Segmenting Scientific Abstracts into Discourse Categories: A Deep Learning-Based Approach for Sparse Labeled Data](https://mlsanity.com/paper/2005.05414/) (2020)
- [Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation](https://mlsanity.com/paper/1910.01462/) (2019)

## Abstract (arXiv)

The abstracts of scientific papers consist of premises and conclusions. Structured abstracts explicitly highlight the conclusion sentences, whereas non-structured abstracts may have conclusion sentences at uncertain positions. This implicit nature of conclusion positions makes the automatic segmentation of scientific abstracts into premises and conclusions a challenging task. In this work, we empirically explore using Normalized Mutual Information (NMI) for abstract segmentation. We consider each abstract as a recurrent cycle of sentences and place segmentation boundaries by greedily optimizing the NMI score between premises and conclusions. On non-structured abstracts, our proposed unsupervised approach GreedyCAS achieves the best performance across all evaluation metrics; on structured abstracts, GreedyCAS outperforms all baseline methods measured by Pk. The strong correlation of NMI to our evaluation metrics reveals the effectiveness of NMI for abstract segmentation.