Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2410.02365 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914963498467328 |
|---|---|
| author | Xie, Haodong Maharjan, Rahul Singh Tavella, Federico Cangelosi, Angelo |
| author_facet | Xie, Haodong Maharjan, Rahul Singh Tavella, Federico Cangelosi, Angelo |
| contents | Understanding and manipulating concrete and abstract concepts is fundamental to human intelligence. Yet, they remain challenging for artificial agents. This paper introduces a multimodal generative approach to high order abstract concept learning, which integrates visual and categorical linguistic information from concrete ones. Our model initially grounds subordinate level concrete concepts, combines them to form basic level concepts, and finally abstracts to superordinate level concepts via the grounding of basic-level concepts. We evaluate the model language learning ability through language-to-visual and visual-to-language tests with high order abstract concepts. Experimental results demonstrate the proficiency of the model in both language understanding and language naming tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02365 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Concrete to Abstract: A Multimodal Generative Approach to Abstract Concept Learning Xie, Haodong Maharjan, Rahul Singh Tavella, Federico Cangelosi, Angelo Computation and Language Artificial Intelligence Understanding and manipulating concrete and abstract concepts is fundamental to human intelligence. Yet, they remain challenging for artificial agents. This paper introduces a multimodal generative approach to high order abstract concept learning, which integrates visual and categorical linguistic information from concrete ones. Our model initially grounds subordinate level concrete concepts, combines them to form basic level concepts, and finally abstracts to superordinate level concepts via the grounding of basic-level concepts. We evaluate the model language learning ability through language-to-visual and visual-to-language tests with high order abstract concepts. Experimental results demonstrate the proficiency of the model in both language understanding and language naming tasks. |
| title | From Concrete to Abstract: A Multimodal Generative Approach to Abstract Concept Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.02365 |