Papers by Jonathan Rawski
Benchmarking Compositionality with Formal Languages (2022.coling-1)
Copied to clipboard
| Challenge: | Compositionality is a hallmark of human language, but it is not yet fully understood . recombining known primitive concepts into larger novel combinations is elusive . |
| Approach: | They use finite-state transducers to make a dataset with controllable compositionality . they find that the models either learn the relations completely or not at all . |
| Outcome: | The proposed model learns the relation completely or not at all on large datasets. |
Transformers as Transducers (2025.tacl-1)
Copied to clipboard
| Challenge: | Using finite transducers, we find that transformers can express large classes of (total functional) transductions. |
| Approach: | They extend existing RASP programming language to sequence-to-sequence transductions and introduce two new extensions. |
| Outcome: | The proposed model can express surprisingly large classes of (total functional) transductions. |