Papers by Charles Torres
Evaluating a Century of Progress on the Cognitive Science of Adjective Ordering (2023.tacl-1)
Copied to clipboard
| Challenge: | a new study examines the performance of cognitive hypotheses for adjective ordering in 32 languages . linguists and cognitive scientists have proposed an array of hypothese predicting adjective ordering . |
| Approach: | They compare the combined performance of existing adjective ordering proposals across 32 languages . they propose to use a baseline that reflects random chance accuracy and a higher baseline that measures idealized order . |
| Outcome: | The proposed hypotheses are compared with baselines in 32 languages and with random and idealized baselines. |
Simpler neural networks prefer subregular languages (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Inductive biases of neural networks are still poorly understood, says dr. johansen . subregular languages are thought to form a bound on human phonological patterns . |
| Approach: | They apply a relaxation of L0 regularization which induces sparsity to study inductive biases of LSTMs. |
| Outcome: | The proposed method is based on a relaxation of L0 regularization, which induces sparsity, and a subregular language bias in LSTMs is related to the cognitive bias observed in human phonology. |