M
Miyoung Ko
Researcher at Korea University
Publications - 14
Citations - 270
Miyoung Ko is an academic researcher from Korea University. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 7, co-authored 12 publications receiving 170 citations.
Papers
More filters
Proceedings ArticleDOI
Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
TL;DR: In this article, the authors introduced paragraph ranker, which ranks paragraphs of retrieved documents for a higher answer recall with less noise and showed that ranking paragraphs and aggregating answers using paragraph Ranker improves performance of open-domain QA pipeline.
Journal ArticleDOI
ReSimNet: drug response similarity prediction using Siamese neural networks.
Minji Jeon,Donghyeon Park,Jinhyuk Lee,Hwisang Jeon,Miyoung Ko,Sunkyu Kim,Yonghwa Choi,Aik Choon Tan,Jaewoo Kang +8 more
TL;DR: Siamese neural networks called ReSimNet can find pairs of compounds that are similar in response even though they may have dissimilar structures, and in the quantitative evaluation, ReSim net outperformed the baseline machine learning models.
Posted Content
Look at the First Sentence: Position Bias in Question Answering
TL;DR: It is found that using the prior distribution of answer positions as a bias model is very effective at reducing position bias recovering the performance of BERT from 35.24% to 81.17% when trained on a biased SQuAD dataset.
Proceedings ArticleDOI
Answering Questions on COVID-19 in Real-Time
Jinhyuk Lee,Sean S. Yi,Minbyul Jeong,Mujeen Sung,Wonjin Yoon,Yonghwa Choi,Miyoung Ko,Jaewoo Kang +7 more
TL;DR: CovidAsk as mentioned in this paper is a QA system that combines biomedical text mining and QA techniques to provide answers to questions in real-time, and leverages information retrieval (IR) approaches to provide entity-level answers that are complementary to QA models.
Proceedings ArticleDOI
Look at the First Sentence: Position Bias in Question Answering
TL;DR: This article showed that using the prior distribution of answer positions as a bias model is very effective at reducing position bias, recovering the performance of BERT from 37.48% to 81.64% when trained on a biased SQuAD dataset.