Di Jin

Dr. Di Jin

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 July 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DJDi Jin
Di Jin
EPEileen Pan
Eileen Pan
NONassim Oufattole
Nassim Oufattole
WWWei-Hung Weng
Wei-Hung Weng
HFHanyi Fang
Hanyi Fang
PSPeter Szolovits
Peter Szolovits
Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a machine comprehension model. Through experiments, we find that even the current best method can only achieve 36.7%, 42.0%, and 70.1% of test accuracy on the English, traditional Chinese, and simplified Chinese questions, respectively. We expect MedQA to present great challenges to existing OpenQA systems and hope that it can serve as a platform to promote much stronger OpenQA models from the NLP community in the future.

4 April 2022 in Computational Linguistics
Verified
Journal Article
Open access
PDF file
DJDi Jin
Di Jin
ZJZhijing Jin
Zhijing Jin
ZHZhiting Hu
Zhiting Hu
OVOlga Vechtomova
Olga Vechtomova
RMRada Mihalcea
Rada Mihalcea
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this article, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017. We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data. We also provide discussions on a variety of important topics regarding the future development of this task.1

4 February 2019 in Biomedical Optics Express
Verified
Journal Article
Open access
PDF file
HZHao Zhang
Hao Zhang
CFChunyu Fang
Chunyu Fang
XXXinlin Xie
Xinlin Xie
YYYicong Yang
Yicong Yang
WMWei Mei
Wei Mei
PFPeng Fei
Peng Fei
We combine a generative adversarial network (GAN) with light microscopy to achieve deep learning super-resolution under a large field of view (FOV). By appropriately adopting prior microscopy data in an adversarial training, the neural network can recover a high-resolution, accurate image of new specimen from its single low-resolution measurement. Its capacity has been broadly demonstrated via imaging various types of samples, such as USAF resolution target, human pathological slides, fluorescence-labelled fibroblast cells, and deep tissues in transgenic mouse brain, by both wide-field and light-sheet microscopes. The gigapixel, multi-color reconstruction of these samples verifies a successful GAN-based single image super-resolution procedure. We also propose an image degrading model to generate low resolution images for training, making our approach free from the complex image registration during training data set preparation. After a well-trained network has been created, this deep learning-based imaging approach is capable of recovering a large FOV (~95 mm2) enhanced resolution of ~1.7 μm at high speed (within 1 second), while not necessarily introducing any changes to the setup of existing microscopes.

21 May 2021 in Preprints.org
Verified
Preprint
Open access
PDF file
DJDi Jin
Di Jin
EPEileen Pan
Eileen Pan
NONassim Oufattole
Nassim Oufattole
WWWei-Hung Weng
Wei-Hung Weng
HFHanyi Fang
Hanyi Fang
PSPeter Szolovits
Peter Szolovits
Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a machine comprehension model. Through experiments, we find that even the current best method can only achieve 36.7%, 42.0%, and 70.1% of test accuracy on the English, traditional Chinese, and simplified Chinese questions, respectively. We expect MedQA to present great challenges to existing OpenQA systems and hope that it can serve as a platform to promote much stronger OpenQA models from the NLP community in the future.

17 January 2022 in WIREs Mechanisms of Disease
Verified
Journal Article
Closed access
PDF file
DJDi Jin
Di Jin
ESElena Sergeeva
Elena Sergeeva
WWWei‐Hung Weng
Wei‐Hung Weng
GCGeeticka Chauhan
Geeticka Chauhan
PSPeter Szolovits
Peter Szolovits

20 June 2019 in arXiv
Verified
Preprint
Open access
PDF file
EAEmily Alsentzer
Emily Alsentzer
JMJohn R. Murphy
John R. Murphy
WBWillie Boag
Willie Boag
WWWei-Hung Weng
Wei-Hung Weng
DJDi Jin
Di Jin
MMMatthew B. A. McDermott
Matthew B. A. McDermott
Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been minimally explored on specialty corpora, such as clinical text; moreover, in the clinical domain, no publicly-available pre-trained BERT models yet exist. In this work, we address this need by exploring and releasing BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically. We demonstrate that using a domain-specific model yields performance improvements on three common clinical NLP tasks as compared to nonspecific embeddings. These domain-specific models are not as performant on two clinical de-identification tasks, and argue that this is a natural consequence of the differences between de-identified source text and synthetically non de-identified task text.