# Learning Disentangled Representations of Texts with Application to Biomedical Abstracts

arXiv: https://arxiv.org/abs/1804.07212 · HTML: https://mlsanity.com/paper/1804.07212/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2018.

## Built on by (most cited first, 9 of 9)

- [Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity](https://mlsanity.com/paper/2111.08366/) (2021)
- [CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example](https://mlsanity.com/paper/2103.12906/) (2021)
- [Disentangling Representations of Text by Masking Transformers](https://mlsanity.com/paper/2104.07155/) (2021)
- [Augmenting Scientific Creativity with Retrieval across Knowledge Domains](https://mlsanity.com/paper/2206.01328/) (2022)
- [Disentangling Learning Representations with Density Estimation](https://mlsanity.com/paper/2302.04362/) (2023)
- [PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning](https://mlsanity.com/paper/2305.02691/) (2023)
- [PropNet: a White-Box and Human-Like Network for Sentence Representation](https://mlsanity.com/paper/2502.10725/) (2025)
- [SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mapping](https://mlsanity.com/paper/2510.11599/) (2025)
- [Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings](https://mlsanity.com/paper/2403.16984/) (2024)

## Abstract (arXiv)

We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability. To induce disentangled embeddings, we propose an adversarial objective based on the (dis)similarity between triplets of documents with respect to specific aspects. Our motivating application is embedding biomedical abstracts describing clinical trials in a manner that disentangles the populations, interventions, and outcomes in a given trial. We show that our method learns representations that encode these clinically salient aspects, and that these can be effectively used to perform aspect-specific retrieval. We demonstrate that the approach generalizes beyond our motivating application in experiments on two multi-aspect review corpora.