Geeticka Chauhan
YOU?
Author Swipe
View article: Training Large ASR Encoders with Differential Privacy
Training Large ASR Encoders with Differential Privacy Open
Self-supervised learning (SSL) methods for large speech models have proven to be highly effective at ASR. With the interest in public deployment of large pre-trained models, there is a rising concern for unintended memorization and leakage…
View article: Improving Medical Visual Representations via Radiology Report Generation
Improving Medical Visual Representations via Radiology Report Generation Open
Vision-language pretraining has been shown to produce high-quality visual encoders which transfer efficiently to downstream computer vision tasks. Contrastive learning approaches have increasingly been adopted for medical vision language p…
View article: RadTex: Learning Efficient Radiograph Representations from Text Reports
RadTex: Learning Efficient Radiograph Representations from Text Reports Open
Automated analysis of chest radiography using deep learning has tremendous potential to enhance the clinical diagnosis of diseases in patients. However, deep learning models typically require large amounts of annotated data to achieve high…
View article: Explainable deep learning in healthcare: A methodological survey from an attribution view
Explainable deep learning in healthcare: A methodological survey from an attribution view Open
The increasing availability of large collections of electronic health record (EHR) data and unprecedented technical advances in deep learning (DL) have sparked a surge of research interest in developing DL based clinical decision support s…
View article: Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View
Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View Open
The increasing availability of large collections of electronic health record (EHR) data and unprecedented technical advances in deep learning (DL) have sparked a surge of research interest in developing DL based clinical decision support s…
View article: How Good Is NLP?A Sober Look at NLP Tasks through the Lens of Social Impact
How Good Is NLP?A Sober Look at NLP Tasks through the Lens of Social Impact Open
Recent years have seen many breakthroughs in natural language processing (NLP), transitioning it from a mostly theoretical field to one with many real-world applications. Noting the rising number of applications of other machine learning a…
View article: How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact Open
Recent years have seen many breakthroughs in natural language processing (NLP), transitioning it from a mostly theoretical field to one with many real-world applications.Noting the rising number of applications of other machine learning an…
View article: MIMIC-Extract
MIMIC-Extract Open
Robust machine learning relies on access to data that can be used with standardized frameworks in important tasks and the ability to develop models whose performance can be reasonably reproduced. In machine learning for healthcare, the com…
View article: MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III
MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III Open
Robust machine learning relies on access to data that can be used with standardized frameworks in important tasks and the ability to develop models whose performance can be reasonably reproduced. In machine learning for healthcare, the com…
View article: REflex: Flexible Framework for Relation Extraction in Multiple Domains
REflex: Flexible Framework for Relation Extraction in Multiple Domains Open
Systematic comparison of methods for relation extraction (RE) is difficult because many experiments in the field are not described precisely enough to be completely reproducible and many papers fail to report ablation studies that would hi…
View article: Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation
Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation Open
Machine learning for healthcare often trains models on de-identified datasets with randomly-shifted calendar dates, ignoring the fact that data were generated under hospital operation practices that change over time. These changing practic…
View article: Data and Code for "A New Approach to Animacy Detection"
Data and Code for "A New Approach to Animacy Detection" Open
This archive contains the code and data for the workshop article "A New Approach to Animacy Detection," published in 2018 in the the 27th International Conference on Computational Linguistics (COLING 2018), in Santa Fe, NM. The root of the…
View article: MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network Open
SemEval 2018 Task 7 tasked participants to build a system to classify two entities within a sentence into one of the 6 possible relation types. We tested 3 classes of models: Linear classifiers, Long Short-Term Memory (LSTM) models, and Co…
View article: Building on Word Animacy to Determine Coreference Chain Animacy in Cultural Narratives
Building on Word Animacy to Determine Coreference Chain Animacy in Cultural Narratives Open
Animacy is the characteristic of being able to independently carry out actions in a story world (e.g., movement, communication). It is a necessary property of characters in stories, and so detecting animacy is an important step in automati…
View article: Building an Ontology for Health Dialogs with Virtual Health Agents
Building an Ontology for Health Dialogs with Virtual Health Agents Open
Virtual Health Agents (VHA) are human-like autonomous intelligent agents built using articial intelligence techniques, specically designed to deliver health interventions that assist patients. By asking the patient questions about their li…
View article: Modeling Occupant-Building-Appliance Interaction for Energy Waste Analysis
Modeling Occupant-Building-Appliance Interaction for Energy Waste Analysis Open
The objective of this paper is to discover the emergent energy performance and determinants of energy waste in buildings. Electricity consumption in the U.S. attributes to 73% of energy waste in buildings and much of this waste is due to i…