Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks
Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architecture. We investigate which architectural factors affect the generalization behavio...
Gorde:
| Egile Nagusiak: | , , |
|---|---|
| Formatua: | Artigo |
| Hizkuntza: | Inglês |
| Argitaratua: |
The MIT Press
2020-07-01
|
| Saila: | Transactions of the Association for Computational Linguistics |
| Sarrera elektronikoa: | https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00304 |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|