# Learning functional sections in medical conversations: iterative pseudo-labeling and human-in-the-loop approach

arXiv: https://arxiv.org/abs/2210.02658 · HTML: https://mlsanity.com/paper/2210.02658/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 6 Oct 2022.

## Builds on (most cited first, 19 of 19)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://mlsanity.com/paper/2006.03659/) (2020)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [Self-training Improves Pre-training for Natural Language Understanding](https://mlsanity.com/paper/2010.02194/) (2020)
- [Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders](https://mlsanity.com/paper/2104.08027/) (2021)
- [Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques](https://mlsanity.com/paper/2005.01795/) (2020)
- [Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures](https://mlsanity.com/paper/2009.08666/) (2020)
- [Dialogue Act Classification with Context-Aware Self-Attention](https://mlsanity.com/paper/1904.02594/) (2019)
- [Semantic Segmentation of Legal Documents via Rhetorical Roles](https://mlsanity.com/paper/2112.01836/) (2021)
- [User Intent Prediction in Information-seeking Conversations](https://mlsanity.com/paper/1901.03489/) (2019)
- [Topic Segmentation and Labeling in Asynchronous Conversations](https://mlsanity.com/paper/1402.0586/) (2014)
- [Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions](https://mlsanity.com/paper/2011.06874/) (2020)
- [Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)](https://mlsanity.com/paper/2107.02565/) (2021)
- [SmartTriage: A system for personalized patient data capture, documentation generation, and decision support](https://mlsanity.com/paper/2010.09905/) (2020)
- [Adding more data does not always help: A study in medical conversation summarization with PEGASUS](https://mlsanity.com/paper/2111.07564/) (2021)

## Built on by (most cited first, 1 of 1)

- [Dialogue-Contextualized Re-ranking for Medical History-Taking](https://mlsanity.com/paper/2304.01974/) (2023)

## Abstract (arXiv)

Medical conversations between patients and medical professionals have implicit functional sections, such as "history taking", "summarization", "education", and "care plan." In this work, we are interested in learning to automatically extract these sections. A direct approach would require collecting large amounts of expert annotations for this task, which is inherently costly due to the contextual inter-and-intra variability between these sections. This paper presents an approach that tackles the problem of learning to classify medical dialogue into functional sections without requiring a large number of annotations. Our approach combines pseudo-labeling and human-in-the-loop. First, we bootstrap using weak supervision with pseudo-labeling to generate dialogue turn-level pseudo-labels and train a transformer-based model, which is then applied to individual sentences to create noisy sentence-level labels. Second, we iteratively refine sentence-level labels using a cluster-based human-in-the-loop approach. Each iteration requires only a few dozen annotator decisions. We evaluate the results on an expert-annotated dataset of 100 dialogues and find that while our models start with 69.5% accuracy, we can iteratively improve it to 82.5%. The code used to perform all experiments described in this paper can be found here: https://github.com/curai/curai-research/tree/main/functional-sections.