Pith. sign in

REVIEW 1 cited by

Jointly Learning to Label Sentences and Tokens

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1811.05949 v1 pith:Q5OCIMIO submitted 2018-11-14 cs.CL cs.LGcs.NE

classification cs.CLcs.LGcs.NE
keywords learningrepresentationsjointlylabellanguagesentencestokensachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Grammatical Error Detection using BERT with Cleaned Lang-8 Dataset

    cs.CL 2024-11 reject novelty 3.0 of 10

    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.

Pith tools