Search Results for author: Dina Demner-Fushman

Found 39 papers, 14 papers with code

Overview of the MedVidQA 2022 Shared Task on Medical Video Question-Answering

no code implementations BioNLP (ACL) 2022 Deepak Gupta, Dina Demner-Fushman

The shared task addressed two of the challenges faced by medical video question answering: (I) a video classification task that explores new approaches to medical video understanding (labeling), and (ii) a visual answer localization task.

Question Answering Video Classification +2

Evidence-based Fact-Checking of Health-related Claims

1 code implementation Findings (EMNLP) 2021 Mourad Sarrouti, Asma Ben Abacha, Yassine Mrabet, Dina Demner-Fushman

Our experiments showed that training deep learning models on real-world medical claims greatly improves performance compared to models trained on synthetic and open-domain claims.

Fact Checking

Overview of the MEDIQA 2021 Shared Task on Summarization in the Medical Domain

no code implementations NAACL (BioNLP) 2021 Asma Ben Abacha, Yassine Mrabet, Yuhao Zhang, Chaitanya Shivade, Curtis Langlotz, Dina Demner-Fushman

The MEDIQA 2021 shared tasks at the BioNLP 2021 workshop addressed three tasks on summarization for medical text: (i) a question summarization task aimed at exploring new approaches to understanding complex real-world consumer health queries, (ii) a multi-answer summarization task that targeted aggregation of multiple relevant answers to a biomedical question into one concise and relevant answer, and (iii) a radiology report summarization task addressing the development of clinically relevant impressions from radiology report findings.

Text Summarization

Enhancing Question Answering by Injecting Ontological Knowledge through Regularization

no code implementations EMNLP (DeeLIO) 2020 Travis Goodwin, Dina Demner-Fushman

Deep neural networks have demonstrated high performance on many natural language processing (NLP) tasks that can be answered directly from text, and have struggled to solve NLP tasks requiring external (e. g., world) knowledge.

Question Answering Semantic Composition

Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches

no code implementations21 Sep 2023 Deepak Gupta, Kush Attal, Dina Demner-Fushman

Toward this, this paper is focused on answering health-related questions asked by the public by providing visual answers from medical videos.

A Dataset for Plain Language Adaptation of Biomedical Abstracts

1 code implementation21 Oct 2022 Kush Attal, Brian Ondov, Dina Demner-Fushman

Therefore, adapting this expert-level language into plain language versions is necessary for the public to reliably comprehend the vast health-related literature.

Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features

1 code implementation5 Oct 2022 Deepak Gupta, Russell Loane, Soumya Gayen, Dina Demner-Fushman

We extensively tested the proposed NNS approach and compared the performance with state-of-the-art NNS approaches on benchmark datasets and our created medical image datasets.

Medical Image Retrieval Retrieval

Clinical Language Understanding Evaluation (CLUE)

no code implementations28 Sep 2022 Travis R. Goodwin, Dina Demner-Fushman

Clinical language processing has received a lot of attention in recent years, resulting in new models or methods for disease phenotyping, mortality prediction, and other tasks.

Mortality Prediction

A Dataset for Medical Instructional Video Classification and Question Answering

2 code implementations30 Jan 2022 Deepak Gupta, Kush Attal, Dina Demner-Fushman

This paper introduces a new challenge and datasets to foster research toward designing systems that can understand medical videos and provide visual answers to natural language questions.

Classification Question Answering +2

Searching for Scientific Evidence in a Pandemic: An Overview of TREC-COVID

no code implementations19 Apr 2021 Kirk Roberts, Tasmeer Alam, Steven Bedrick, Dina Demner-Fushman, Kyle Lo, Ian Soboroff, Ellen Voorhees, Lucy Lu Wang, William R Hersh

We present an overview of the TREC-COVID Challenge, an information retrieval (IR) shared task to evaluate search on scientific literature related to COVID-19.

Information Retrieval Retrieval

HOLMS: Alternative Summary Evaluation with Large Language Models

no code implementations COLING 2020 Yassine Mrabet, Dina Demner-Fushman

Efficient document summarization requires evaluation measures that can not only rank a set of systems based on an average score, but also highlight which individual summary is better than another.

Document Summarization Extractive Summarization

Visual Question Generation from Radiology Images

1 code implementation WS 2020 Mourad Sarrouti, Asma Ben Abacha, Dina Demner-Fushman

Visual Question Generation (VQG), the task of generating a question based on image contents, is an increasingly important area that combines natural language processing and computer vision.

Image Augmentation Question Generation +3

Question-Driven Summarization of Answers to Consumer Health Questions

1 code implementation18 May 2020 Max Savery, Asma Ben Abacha, Soumya Gayen, Dina Demner-Fushman

This dataset can be used to evaluate single or multi-document summaries generated by algorithms using extractive or abstractive approaches.

Question Answering

TREC-COVID: Constructing a Pandemic Information Retrieval Test Collection

no code implementations9 May 2020 Ellen Voorhees, Tasmeer Alam, Steven Bedrick, Dina Demner-Fushman, William R Hersh, Kyle Lo, Kirk Roberts, Ian Soboroff, Lucy Lu Wang

TREC-COVID is a community evaluation designed to build a test collection that captures the information needs of biomedical researchers using the scientific literature during a pandemic.

Information Retrieval Retrieval

Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge

no code implementations16 Oct 2019 Travis R. Goodwin, Dina Demner-Fushman

In this paper we present OSCAR (Ontology-based Semantic Composition Augmented Regularization), a method for injecting task-agnostic knowledge from an Ontology or knowledge graph into a neural network during pretraining.

Question Answering Semantic Composition

Overview of the MEDIQA 2019 Shared Task on Textual Inference, Question Entailment and Question Answering

1 code implementation WS 2019 Asma Ben Abacha, Chaitanya Shivade, Dina Demner-Fushman

MEDIQA 2019 includes three tasks: Natural Language Inference (NLI), Recognizing Question Entailment (RQE), and Question Answering (QA) in the medical domain.

Information Retrieval Natural Language Inference +2

A Question-Entailment Approach to Question Answering

3 code implementations23 Jan 2019 Asma Ben Abacha, Dina Demner-Fushman

One of the challenges in large-scale information retrieval (IR) is to develop fine-grained and domain-specific methods to answer natural language questions.

Information Retrieval Question Answering +2

A dataset of clinically generated visual questions and answers about radiology images

no code implementations Scientific Data 2018 Jason J. Lau, Soumya Gayen, Asma Ben Abacha, Dina Demner-Fushman

We introduce VQA-RAD, the first manually constructed dataset where clinicians asked naturally occurring questions about radiology images and provided reference answers.

Decision Making Medical Visual Question Answering +2

TextFlow: A Text Similarity Measure based on Continuous Sequences

no code implementations ACL 2017 Yassine Mrabet, Halil Kilicoglu, Dina Demner-Fushman

Text similarity measures are used in multiple tasks such as plagiarism detection, information ranking and recognition of paraphrases and textual entailment.

Natural Language Inference Text Generation +1

Annotating Logical Forms for EHR Questions

no code implementations LREC 2016 Kirk Roberts, Dina Demner-Fushman

From these, 468 specific questions are found containing 259 unique medical concepts and requiring 53 unique predicates to represent the logical forms.

Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation

1 code implementation CVPR 2016 Hoo-chang Shin, Kirk Roberts, Le Lu, Dina Demner-Fushman, Jianhua Yao, Ronald M. Summers

Recurrent neural networks (RNNs) are then trained to describe the contexts of a detected disease, based on the deep CNN features.

Cannot find the paper you are looking for? You can Submit a new open access paper.