Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118802803> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3118802803 abstract "Grammatical Error Correction (GEC) seriously suffers from a scarcity of data, both annotated and unannotated, as humans do not intentionally make grammatical errors. To account for this, we make use of the plentiful unlabeled plain text available and augment a dataset with artificial noise to increase our effective training data and pre-train our model as a denoising autoencoder (DAE), which offers an intuitive data augmentation solution for GEC. In a novel approach, we enhance our DAE, a Transformer Model, with a cross-document context mechanism and use a parallel encoder to encode the cross-document context before fusing the two contexts of the encoders in the decoder. Supplied by the combination of document similarity metrics and any unlabeled plain text, this serves as a new method of equipping a GEC model with supplemental context and allowing it to glean grammatical information from a separate plain text corpus. We evaluate our model on the CoNLL-2014 GEC Shared Task and achieve results that approach state-of-the-art for single models and show great potential with ever available and plentiful plain text." @default.
- W3118802803 created "2021-01-18" @default.
- W3118802803 creator A5002584135 @default.
- W3118802803 creator A5036050911 @default.
- W3118802803 creator A5043225662 @default.
- W3118802803 date "2020-12-04" @default.
- W3118802803 modified "2023-09-24" @default.
- W3118802803 title "Grammatical Error Correction: More Data with More Context" @default.
- W3118802803 cites W2025768430 @default.
- W3118802803 cites W2098297786 @default.
- W3118802803 cites W2128878007 @default.
- W3118802803 cites W2589277916 @default.
- W3118802803 cites W2606974598 @default.
- W3118802803 cites W2785047343 @default.
- W3118802803 cites W2798542795 @default.
- W3118802803 cites W2885421725 @default.
- W3118802803 cites W2895358146 @default.
- W3118802803 cites W2925188774 @default.
- W3118802803 cites W2933138175 @default.
- W3118802803 cites W2936597270 @default.
- W3118802803 cites W2948335087 @default.
- W3118802803 cites W2963655793 @default.
- W3118802803 cites W2963881719 @default.
- W3118802803 cites W2964082031 @default.
- W3118802803 cites W2964165364 @default.
- W3118802803 cites W2970429618 @default.
- W3118802803 cites W2970521905 @default.
- W3118802803 cites W2998230451 @default.
- W3118802803 cites W3035010485 @default.
- W3118802803 cites W3037162118 @default.
- W3118802803 doi "https://doi.org/10.1109/ialp51396.2020.9310498" @default.
- W3118802803 hasPublicationYear "2020" @default.
- W3118802803 type Work @default.
- W3118802803 sameAs 3118802803 @default.
- W3118802803 citedByCount "4" @default.
- W3118802803 countsByYear W31188028032021 @default.
- W3118802803 countsByYear W31188028032023 @default.
- W3118802803 crossrefType "proceedings-article" @default.
- W3118802803 hasAuthorship W3118802803A5002584135 @default.
- W3118802803 hasAuthorship W3118802803A5036050911 @default.
- W3118802803 hasAuthorship W3118802803A5043225662 @default.
- W3118802803 hasConcept C104317684 @default.
- W3118802803 hasConcept C111919701 @default.
- W3118802803 hasConcept C118505674 @default.
- W3118802803 hasConcept C119857082 @default.
- W3118802803 hasConcept C121332964 @default.
- W3118802803 hasConcept C148730421 @default.
- W3118802803 hasConcept C151730666 @default.
- W3118802803 hasConcept C154945302 @default.
- W3118802803 hasConcept C165801399 @default.
- W3118802803 hasConcept C185592680 @default.
- W3118802803 hasConcept C204321447 @default.
- W3118802803 hasConcept C2779343474 @default.
- W3118802803 hasConcept C41008148 @default.
- W3118802803 hasConcept C46503548 @default.
- W3118802803 hasConcept C55493867 @default.
- W3118802803 hasConcept C62520636 @default.
- W3118802803 hasConcept C66322947 @default.
- W3118802803 hasConcept C66746571 @default.
- W3118802803 hasConcept C86803240 @default.
- W3118802803 hasConceptScore W3118802803C104317684 @default.
- W3118802803 hasConceptScore W3118802803C111919701 @default.
- W3118802803 hasConceptScore W3118802803C118505674 @default.
- W3118802803 hasConceptScore W3118802803C119857082 @default.
- W3118802803 hasConceptScore W3118802803C121332964 @default.
- W3118802803 hasConceptScore W3118802803C148730421 @default.
- W3118802803 hasConceptScore W3118802803C151730666 @default.
- W3118802803 hasConceptScore W3118802803C154945302 @default.
- W3118802803 hasConceptScore W3118802803C165801399 @default.
- W3118802803 hasConceptScore W3118802803C185592680 @default.
- W3118802803 hasConceptScore W3118802803C204321447 @default.
- W3118802803 hasConceptScore W3118802803C2779343474 @default.
- W3118802803 hasConceptScore W3118802803C41008148 @default.
- W3118802803 hasConceptScore W3118802803C46503548 @default.
- W3118802803 hasConceptScore W3118802803C55493867 @default.
- W3118802803 hasConceptScore W3118802803C62520636 @default.
- W3118802803 hasConceptScore W3118802803C66322947 @default.
- W3118802803 hasConceptScore W3118802803C66746571 @default.
- W3118802803 hasConceptScore W3118802803C86803240 @default.
- W3118802803 hasFunder F4320321001 @default.
- W3118802803 hasFunder F4320337504 @default.
- W3118802803 hasLocation W31188028031 @default.
- W3118802803 hasOpenAccess W3118802803 @default.
- W3118802803 hasPrimaryLocation W31188028031 @default.
- W3118802803 hasRelatedWork W2275988210 @default.
- W3118802803 hasRelatedWork W2359640100 @default.
- W3118802803 hasRelatedWork W2948211076 @default.
- W3118802803 hasRelatedWork W2966024403 @default.
- W3118802803 hasRelatedWork W3092611869 @default.
- W3118802803 hasRelatedWork W3101728549 @default.
- W3118802803 hasRelatedWork W3116268265 @default.
- W3118802803 hasRelatedWork W3173378776 @default.
- W3118802803 hasRelatedWork W4287643787 @default.
- W3118802803 hasRelatedWork W4378499193 @default.
- W3118802803 isParatext "false" @default.
- W3118802803 isRetracted "false" @default.
- W3118802803 magId "3118802803" @default.
- W3118802803 workType "article" @default.