mlsanityData to 14 Oct 2026

Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information

arXiv 2305.11553 ↗First posted 19 May 2023cs.CLcited by 0

Not on the map. Why?

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.

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

18 of 41 references.

References · 18

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2019On Variational Bounds of Mutual Informationcited by 559
  3. 2017PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstractscited by 124
  4. 2018Text Segmentation as a Supervised Learning Taskcited by 76
  5. 2020Text Segmentation by Cross Segment Attentioncited by 54
  6. 2019Argument Generation with Retrieval, Planning, and Realizationcited by 45
  7. 2020Aspect-Controlled Neural Argument Generationcited by 43
  8. 2020Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentationcited by 41
  9. 2021Unsupervised Topic Segmentation of Meetings with BERT Embeddingscited by 30
  10. 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
  11. 2018Attention-based Neural Text Segmentationcited by 26
  12. 2021Unsupervised Extractive Summarization using Pointwise Mutual Informationcited by 23
6 more
  1. 2021Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherencecited by 22
  2. 2019Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learningcited by 12
  3. 2015Text Segmentation based on Semantic Word Embeddingscited by 11
  4. 2020Structural Text Segmentation of Legal Documentscited by 11
  5. 2020Segmenting Scientific Abstracts into Discourse Categories: A Deep Learning-Based Approach for Sparse Labeled Datacited by 5
  6. 2019Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generationcited by 3

Built on by

Not cited yet.