Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2406.08787 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913582232371200 |
|---|---|
| author | Sinha, Sania Premsri, Tanawan Kordjamshidi, Parisa |
| author_facet | Sinha, Sania Premsri, Tanawan Kordjamshidi, Parisa |
| contents | Compositional learning, mastering the ability to combine basic concepts and construct more intricate ones, is crucial for human cognition, especially in human language comprehension and visual perception. This notion is tightly connected to generalization over unobserved situations. Despite its integral role in intelligence, there is a lack of systematic theoretical and experimental research methodologies, making it difficult to analyze the compositional learning abilities of computational models. In this paper, we survey the literature on compositional learning of AI models and the connections made to cognitive studies. We identify abstract concepts of compositionality in cognitive and linguistic studies and connect these to the computational challenges faced by language and vision models in compositional reasoning. We overview the formal definitions, tasks, evaluation benchmarks, various computational models, and theoretical findings. Our primary focus is on linguistic benchmarks and combining language and vision, though there is a large amount of research on compositional concept learning in the computer vision community alone. We cover modern studies on large language models to provide a deeper understanding of the cutting-edge compositional capabilities exhibited by state-of-the-art AI models and pinpoint important directions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08787 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices Sinha, Sania Premsri, Tanawan Kordjamshidi, Parisa Artificial Intelligence Compositional learning, mastering the ability to combine basic concepts and construct more intricate ones, is crucial for human cognition, especially in human language comprehension and visual perception. This notion is tightly connected to generalization over unobserved situations. Despite its integral role in intelligence, there is a lack of systematic theoretical and experimental research methodologies, making it difficult to analyze the compositional learning abilities of computational models. In this paper, we survey the literature on compositional learning of AI models and the connections made to cognitive studies. We identify abstract concepts of compositionality in cognitive and linguistic studies and connect these to the computational challenges faced by language and vision models in compositional reasoning. We overview the formal definitions, tasks, evaluation benchmarks, various computational models, and theoretical findings. Our primary focus is on linguistic benchmarks and combining language and vision, though there is a large amount of research on compositional concept learning in the computer vision community alone. We cover modern studies on large language models to provide a deeper understanding of the cutting-edge compositional capabilities exhibited by state-of-the-art AI models and pinpoint important directions for future research. |
| title | A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2406.08787 |