Papers by Daesik Kim
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. |