Construction and Completion of Document-Level Multimodal Question and Answer Knowledge Graph

DOI

10.2991/978-94-6463-638-3_46How to use a DOI?

Keywords

Multimodal Question and Answer Knowledge Graph; Knowledge Graph Completion Virtual Q&A Community

Abstract

To make full use of the documents in question and answer (Q&A) community with text and image information included, improving the ability of information retrieval and semantic understanding, this paper focuses on the construction and completion of a multimodal Q&A knowledge graph. Firstly, we propose a document-level multimodal question and answer knowledge graph (DMQAKG), using topic, question, and answer documents as nodes, and building document relations. Furthermore, we also propose a multimodal Q&A knowledge graph completion method (MQAKGC) for DMQAKG based on multimodal feature extraction and fusion and multimodal knowledge graph link prediction. We use graph convolutional network (GCN) to capture the constructional features and long-short term memory (LSTM) to learn the chronological dependency between the entities for further completion of the missing relations. Experimental results show the superior performance of the proposed knowledge graph completion method in different Q&A subset scales.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xiaoyi Zhang
PY  - 2024
DA  - 2024/12/30
TI  - Construction and Completion of Document-Level Multimodal Question and Answer Knowledge Graph
BT  - Proceedings of the 5th International Conference on Economic Management and Big Data Application (ICEMBDA 2024)
PB  - Atlantis Press
SP  - 467
EP  - 473
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-638-3_46
DO  - 10.2991/978-94-6463-638-3_46
ID  - Zhang2024
ER  -