Papers by Shahar Jacob
FAME: Flexible, Scalable Analogy Mappings Engine (2023.emnlp-main)
Copied to clipboard
| Challenge: | Most work on computational analogy relies heavily on complex, manually crafted input. |
| Approach: | They propose to use commonsense representations to identify mappings between entities and use them to interpret their output. |
| Outcome: | The proposed model outperforms human models on large analogy problems and outperfies human predictions. |