Close this dialog
source link: https://ieeexplore.ieee.org/document/10059210
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Weakly Supervised Concept Map Generation Through Task-Guided Graph Translation
Weakly Supervised Concept Map Generation Through Task-Guided Graph Translation | IEEE Journals & Magazine | IEEE Xplore
I. Introduction
Standing out for the clear and concise structured knowledge representation, concept maps have been widely applied in knowledge management [1], [2], document summarization [3], [4], information retrieval [5] and educational science [6], [7]. Fig. 1 shows toy examples of concept maps derived from a document describing “Moon Landing”, where nodes in the graph indicate important concepts and links reflect interactions among concepts. Although concept maps are helpful in both providing interpretable representations of texts and boosting the performance of downstream tasks, the creation of concept maps is challenging and time-consuming.
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK