7.5k citations · 8.9k across the 37 of their papers we have counts for
7 papers · 2 filters
Learning Dense Representations of Phrases at Scale
Jinhyuk Lee, Mujeen Sung, Jaewoo Kang +1
Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019). However,…
Transferability of Natural Language Inference to Biomedical Question Answering
Minbyul Jeong, Mujeen Sung, Gangwoo Kim +4
Biomedical question answering (QA) is a challenging task due to the scarcity of data and the requirement of domain expertise. Pre-trained language models have been used to address…
Answering Questions on COVID-19 in Real-Time
Jinhyuk Lee, Sean S. Yi, Minbyul Jeong +5
The recent outbreak of the novel coronavirus is wreaking havoc on the world and researchers are struggling to effectively combat it. One reason why the fight is difficult is due to…
Biomedical Entity Representations with Synonym Marginalization
Mujeen Sung, Hwisang Jeon, Jinhyuk Lee +1
Biomedical named entities often play important roles in many biomedical text mining tools. However, due to the incompleteness of provided synonyms and numerous variations in their…
Look at the First Sentence: Position Bias in Question Answering
Miyoung Ko, Jinhyuk Lee, Hyunjae Kim +2
Many extractive question answering models are trained to predict start and end positions of answers. The choice of predicting answers as positions is mainly due to its simplicity a…
Adversarial Subword Regularization for Robust Neural Machine Translation
Jungsoo Park, Mujeen Sung, Jinhyuk Lee +1
Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword…
Learning by Semantic Similarity Makes Abstractive Summarization Better
Wonjin Yoon, Yoon Sun Yeo, Minbyul Jeong +2
By harnessing pre-trained language models, summarization models had rapid progress recently. However, the models are mainly assessed by automatic evaluation metrics such as ROUGE.…