| Autor: |
Pillai, Nisha, Matuszek, Cynthia, Ferraro, Francis |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
2021 30th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) |
| Druh dokumentu: |
Working Paper |
| Popis: |
We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning of language about a wide range of real-world objects. We evaluate the efficacy of this learning by predicting the semantics of objects and comparing the performance with neural and non-neural inputs. We show that this generative approach exhibits promising results in language grounding without pre-specifying visual categories under low resource settings. Our experiments demonstrate that this approach is generalizable to multilingual, highly varied datasets. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
