Fine-tuning BERT-base-uncased on a hand-cleaned Lang-8 subset yields F1 0.91 on that same distribution, but the result is not benchmarked against standard GED tests.
Jointly Learning to Label Sentences and Tokens
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language composition can allow us to guide the models based on existing knowledge, regularizing them towards more robust and interpretable representations. In this paper, we investigate how objectives at different granularities can be used to learn better language representations and we propose an architecture for jointly learning to label sentences and tokens. The predictions at each level are combined together using an attention mechanism, with token-level labels also acting as explicit supervision for composing sentence-level representations. Our experiments show that by learning to perform these tasks jointly on multiple levels, the model achieves substantial improvements for both sentence classification and sequence labeling.
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Enhancing Grammatical Error Detection using BERT with Cleaned Lang-8 Dataset
Fine-tuning BERT-base-uncased on a hand-cleaned Lang-8 subset yields F1 0.91 on that same distribution, but the result is not benchmarked against standard GED tests.