no code implementations • 26 Mar 2024 • Linyang He, Peili Chen, Ercong Nie, Yuanning Li, Jonathan R. Brennan
4) For Transformer-based models, both embeddings and attentions capture grammatical features but show distinct patterns.
no code implementations • 28 Oct 2022 • Miloš Stanojević, Jonathan R. Brennan, Donald Dunagan, Mark Steedman, John T. Hale
These effects are spatially distinct from bilateral superior temporal effects that are unique to predictability.
no code implementations • ACL 2018 • John Hale, Chris Dyer, Adhiguna Kuncoro, Jonathan R. Brennan
Model comparisons attribute the early peak to syntactic composition within the RNNG.