A quantum‐like approach for text generation from knowledge graphs
Abstract Recent text generation methods frequently learn node representations from graph‐based data via global or local aggregation, such as knowledge graphs. Since all nodes are connected directly, node global representation encoding enables direct communication between two distant nodes while disr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-12-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12178 |
| _version_ | 1797383476163379200 |
|---|---|
| author | Jia Zhu Xiaodong Ma Zhihao Lin Pasquale DeMeo |
| author_facet | Jia Zhu Xiaodong Ma Zhihao Lin Pasquale DeMeo |
| author_sort | Jia Zhu |
| collection | DOAJ |
| description | Abstract Recent text generation methods frequently learn node representations from graph‐based data via global or local aggregation, such as knowledge graphs. Since all nodes are connected directly, node global representation encoding enables direct communication between two distant nodes while disregarding graph topology. Node local representation encoding, which captures the graph structure, considers the connections between nearby nodes but misses out onlong‐range relations. A quantum‐like approach to learning better‐contextualised node embeddings is proposed using a fusion model that combines both encoding strategies. Our methods significantly improve on two graph‐to‐text datasets compared to state‐of‐the‐art models in various experiments. |
| first_indexed | 2024-03-08T21:21:33Z |
| format | Article |
| id | doaj.art-a83197e8b28842e1ad5e42744067f77f |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-03-08T21:21:33Z |
| publishDate | 2023-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-a83197e8b28842e1ad5e42744067f77f2023-12-21T09:45:29ZengWileyCAAI Transactions on Intelligence Technology2468-23222023-12-01841455146310.1049/cit2.12178A quantum‐like approach for text generation from knowledge graphsJia Zhu0Xiaodong Ma1Zhihao Lin2Pasquale DeMeo3Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Jinhua ChinaKey Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Jinhua ChinaSchool of Computer Science South China Normal University Guangzhou ChinaDICAM Department University of Messina Messina ItalyAbstract Recent text generation methods frequently learn node representations from graph‐based data via global or local aggregation, such as knowledge graphs. Since all nodes are connected directly, node global representation encoding enables direct communication between two distant nodes while disregarding graph topology. Node local representation encoding, which captures the graph structure, considers the connections between nearby nodes but misses out onlong‐range relations. A quantum‐like approach to learning better‐contextualised node embeddings is proposed using a fusion model that combines both encoding strategies. Our methods significantly improve on two graph‐to‐text datasets compared to state‐of‐the‐art models in various experiments.https://doi.org/10.1049/cit2.12178data miningknowledge‐based visionmachine learningnatural language processingtext analysis |
| spellingShingle | Jia Zhu Xiaodong Ma Zhihao Lin Pasquale DeMeo A quantum‐like approach for text generation from knowledge graphs CAAI Transactions on Intelligence Technology data mining knowledge‐based vision machine learning natural language processing text analysis |
| title | A quantum‐like approach for text generation from knowledge graphs |
| title_full | A quantum‐like approach for text generation from knowledge graphs |
| title_fullStr | A quantum‐like approach for text generation from knowledge graphs |
| title_full_unstemmed | A quantum‐like approach for text generation from knowledge graphs |
| title_short | A quantum‐like approach for text generation from knowledge graphs |
| title_sort | quantum like approach for text generation from knowledge graphs |
| topic | data mining knowledge‐based vision machine learning natural language processing text analysis |
| url | https://doi.org/10.1049/cit2.12178 |
| work_keys_str_mv | AT jiazhu aquantumlikeapproachfortextgenerationfromknowledgegraphs AT xiaodongma aquantumlikeapproachfortextgenerationfromknowledgegraphs AT zhihaolin aquantumlikeapproachfortextgenerationfromknowledgegraphs AT pasqualedemeo aquantumlikeapproachfortextgenerationfromknowledgegraphs AT jiazhu quantumlikeapproachfortextgenerationfromknowledgegraphs AT xiaodongma quantumlikeapproachfortextgenerationfromknowledgegraphs AT zhihaolin quantumlikeapproachfortextgenerationfromknowledgegraphs AT pasqualedemeo quantumlikeapproachfortextgenerationfromknowledgegraphs |