Papers by Jan-Willem van de Meent
Disentangling Representations of Text by Masking Transformers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Large pretrained models such as BERT encode a range of features into monolithic vectors, providing strong predictive accuracy across downstream tasks. |
| Approach: | They explore whether it is possible to learn disentangled representations by identifying existing subnetworks within pretrained models that encode distinct, complementary aspects. |
| Outcome: | The proposed method disentangles sentiment from genre in movie reviews, toxicity from dialect in Tweets, and syntax from semantics. |
Learning Disentangled Representations of Texts with Application to Biomedical Abstracts (D18-1)
Copied to clipboard
| Challenge: | a method for learning disentangled representations of texts that encode distinct and complementary aspects is proposed . a classic problem in distributed representation learning is that it is difficult to determine what information individual dimensions encode. |
| Approach: | They propose a method for learning disentangled representations of texts that encode distinct and complementary aspects by a adversarial objective based on the (dis)similarity between triplets of documents with respect to specific aspects. |
| Outcome: | The proposed method can be used to perform aspect-specific retrieval on biomedical abstracts. |
Towards Reducing Diagnostic Errors with Interpretable Risk Prediction (2024.naacl-long)
Copied to clipboard
Denis McInerney, William Dickinson, Lucy Flynn, Andrea Young, Geoffrey Young, Jan-Willem van de Meent, Byron Wallace
| Challenge: | Diagnostic errors occur because clinicians cannot easily access relevant information in EHRs. |
| Approach: | They propose a method to use LLMs to identify pieces of evidence that indicate increased or decreased risk of specific diagnoses in patient EHRs. |
| Outcome: | The proposed method reduces diagnostic errors by identifying evidence in patient EHRs . it uses a Neural Additive Model to make predictions backed by evidence at time-points where clinicians are uncertain . |
On the Impact of Random Seeds on the Fairness of Clinical Classifiers (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work has shown that fine-tuning large networks is surprisingly sensitive to changes in random seed(s). |
| Approach: | They explore the implications of this phenomenon for model fairness across demographic groups in clinical prediction tasks over electronic health records (EHR) they find that jointly optimizing for high overall performance and low disparities does not yield statistically significant improvements. |
| Outcome: | The proposed model fairness is based on the MIMIC-III dataset, the standard dataset in clinical NLP research. |
CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study suggests that linear models with interpretable features are more reliable than opaque models. |
| Approach: | They propose an approach for natural-language specification of features for linear models . they prompt LLMs with expert-crafted queries to generate interpretable features from health records . |
| Outcome: | The proposed approach can be used to craft features clinically meaningful for downstream tasks . it is based on a risk prediction task and standard predictive tasks based upon this data . |
That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent multimodal models induce soft local alignments between image regions and sentences. |
| Approach: | They compare alignments from a state-of-the-art multimodal model for EHR with human annotations that link image regions to sentences. |
| Outcome: | The proposed models induce soft local alignments between image regions and sentences . the text has an often weak or unintuitive influence on attention, the authors found . |