S
Sahar Kazemzadeh
Publications - 3
Citations - 851
Sahar Kazemzadeh is an academic researcher. The author has contributed to research in topics: Internal medicine & Natural language. The author has an hindex of 1, co-authored 1 publications receiving 597 citations.
Papers
More filters
Proceedings ArticleDOI
ReferItGame: Referring to Objects in Photographs of Natural Scenes
TL;DR: A new game to crowd-source natural language referring expressions by designing a two player game that can both collect and verify referring expressions directly within the game and provides an in depth analysis of the resulting dataset.
Journal ArticleDOI
Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists.
Sahar Kazemzadeh,Jin Yu,Shahar Jamshy,Rory Pilgrim,Zaid Nabulsi,Christina Chen,Neeral Beladia,Charles Lau,Scott Mayer McKinney,Thad Hughes,Atilla Peter Kiraly,Sreenivasa Raju Kalidindi,Monde Muyoyeta,Jameson Malemela,Ting-Fang Shih,Greg S. Corrado,Lily Peng,Katherine Chou,Po-Hsuan Cameron Chen,Yun Liu,Krish Eswaran,Daniel Tse,Shravya Shetty,Shruthi Prabhakara +23 more
TL;DR: A deep learning method was found to be noninferior to radiologists for the determination of active tuberculosis on digital chest radiographs and its performance was compared with that of radiologists.
BERT-based Multi-task Learning
TL;DR: This article implemented a BERT Transformers model that predicts sentiment, detects paraphrases and predicts semantic textual similarity (STS) on the test sets, achieving 86.5% accuracy on paraphrase detection, 50% accuracy in sentiment analysis, and an STS correlation coefficient of 76.1%.