S
Seonhoon Kim
Researcher at Seoul National University
Publications - 18
Citations - 327
Seonhoon Kim is an academic researcher from Seoul National University. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 5, co-authored 12 publications receiving 235 citations. Previous affiliations of Seonhoon Kim include Naver Corporation.
Papers
More filters
Journal ArticleDOI
Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
TL;DR: A densely-connected co-attentive recurrent neural network, each layer of which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers, which achieves state-of-the-art performances for most of the tasks.
Posted Content
Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
TL;DR: The authors proposed a densely-connected co-attentive recurrent neural network (C-RNN), which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers.
Posted Content
Self-supervised pre-training and contrastive representation learning for multiple-choice video QA
TL;DR: A self-supervised pre-training stage and a supervised contrastive learning in the main stage as an auxiliary learning are proposed for multiple-choice video question answering with state-of-the-art performance on all datasets.
Proceedings ArticleDOI
Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension.
TL;DR: A novel algorithm for solving the textbook question answering (TQA) task is introduced which describes more realistic QA problems compared to other recent tasks and a novel self-supervised open-set learning process without any annotations is introduced.