activity
20132021
most citedUnderstanding Heart-Failure Patients EHR Clinical Features via SHAP Interpretation of Tree-Based Machine Learning Model Predictions

36 citations · 75 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG202136 cited

Understanding Heart-Failure Patients EHR Clinical Features via SHAP Interpretation of Tree-Based Machine Learning Model Predictions

Shuyu Lu, Ruoyu Chen, Wei Wei +1

Heart failure (HF) is a major cause of mortality. Accurately monitoring HF progress and adjust therapies are critical for improving patient outcomes. An experienced cardiologist ca…

cs.LG2020

Learning Latent Causal Structures with a Redundant Input Neural Network

Jonathan D. Young, Bryan Andrews, Gregory F. Cooper +1

Most causal discovery algorithms find causal structure among a set of observed variables. Learning the causal structure among latent variables remains an important open problem, pa…

cs.LG20191 cited

Supervised Vector Quantized Variational Autoencoder for Learning Interpretable Global Representations

Yifan Xue, Michael Ding, Xinghua Lu

Learning interpretable representations of data remains a central challenge in deep learning. When training a deep generative model, the observed data are often associated with cert…

cs.CL2019

PubMedQA: A Dataset for Biomedical Research Question Answering

Qiao Jin, Bhuwan Dhingra, Zhengping Liu +2

We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. The task of PubMedQA is to answer research questions with yes/no/maybe (e…

cs.CL20199 cited

Deep Contextualized Biomedical Abbreviation Expansion

Qiao Jin, Jinling Liu, Xinghua Lu

Automatic identification and expansion of ambiguous abbreviations are essential for biomedical natural language processing applications, such as information retrieval and question…

cs.CL201929 cited

Probing Biomedical Embeddings from Language Models

Qiao Jin, Bhuwan Dhingra, William W. Cohen +1

Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such a…