Papers by Daesik Kim

1 papers
Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension (P19-1)

Copied to clipboard

Challenge: In a decade, question answering (QA) has been one of the most promising achievements in the field of natural language processing (NLP).
Approach: They propose a new module f-GCN based on graph convolutional networks (GCN) to extract knowledge features from multi-modal contexts in complex input data.
Outcome: The proposed model outperforms state-of-the-art methods on the textbook question answering task and on the visual features of the dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations