Structural Supervision Improves Learning of Non-Local Grammatical Dependencies

© 2019 Association for Computational Linguistics State-of-the-art LSTM language models trained on large corpora learn sequential contingencies in impressive detail and have been shown to acquire a number of non-local grammatical dependencies with some success. Here we investigate whether supervision...

Full beskrivning

Bibliografiska uppgifter
Materialtyp: Artikel
Språk:English
Publicerad: Association for Computational Linguistics 2021
Länkar:https://hdl.handle.net/1721.1/137340