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...
Format: | Article |
---|---|
Language: | English |
Published: |
Association for Computational Linguistics,
2021-11-04T15:04:54Z.
|
Subjects: | |
Online Access: | Get fulltext |