Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215857809> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W3215857809 abstract "The use of transfer learning in Natural Language Processing (NLP) has grown over the last few years. Large, pre-trained neural networks based on the Transformer architecture are one example of this, achieving state-of-theart performance on several commonly used performance benchmarks, often when finetuned on a downstream task. Another form of transfer learning, Multitask Learning, has also been shown to improve performance in Natural Language Processing tasks and increase model robustness. This paper outlines preliminary findings of investigations into the impact of using pretrained language models alongside multitask fine-tuning to create an automated marking system of second language learners’ written English. Using multiple transformer models and multiple datasets, this study compares different combinations of models and tasks and evaluates their impact on the performance of an automated marking system This presentation is a snap-shot of work being conducted as part of my dissertation for the University of Wolverhampton’s Computational Linguistics Masters’ programme." @default.
- W3215857809 created "2021-12-06" @default.
- W3215857809 creator A5045703737 @default.
- W3215857809 date "2021-01-01" @default.
- W3215857809 modified "2023-09-23" @default.
- W3215857809 title "Using Transfer Learning to Automatically Mark L2 Writing Texts" @default.
- W3215857809 cites W1549393725 @default.
- W3215857809 cites W1969967679 @default.
- W3215857809 cites W2105845572 @default.
- W3215857809 cites W2124725212 @default.
- W3215857809 cites W2147800946 @default.
- W3215857809 cites W2250372169 @default.
- W3215857809 cites W2518290665 @default.
- W3215857809 cites W2564237127 @default.
- W3215857809 cites W2598494004 @default.
- W3215857809 cites W2797885244 @default.
- W3215857809 cites W2803521238 @default.
- W3215857809 cites W2911964244 @default.
- W3215857809 cites W2963341956 @default.
- W3215857809 cites W2978670439 @default.
- W3215857809 cites W2979736514 @default.
- W3215857809 cites W3034738758 @default.
- W3215857809 doi "https://doi.org/10.26615/issn.2603-2821.2021_008" @default.
- W3215857809 hasPublicationYear "2021" @default.
- W3215857809 type Work @default.
- W3215857809 sameAs 3215857809 @default.
- W3215857809 citedByCount "0" @default.
- W3215857809 crossrefType "proceedings-article" @default.
- W3215857809 hasAuthorship W3215857809A5045703737 @default.
- W3215857809 hasBestOaLocation W32158578091 @default.
- W3215857809 hasConcept C150899416 @default.
- W3215857809 hasConcept C154945302 @default.
- W3215857809 hasConcept C173608175 @default.
- W3215857809 hasConcept C204321447 @default.
- W3215857809 hasConcept C2776175482 @default.
- W3215857809 hasConcept C41008148 @default.
- W3215857809 hasConceptScore W3215857809C150899416 @default.
- W3215857809 hasConceptScore W3215857809C154945302 @default.
- W3215857809 hasConceptScore W3215857809C173608175 @default.
- W3215857809 hasConceptScore W3215857809C204321447 @default.
- W3215857809 hasConceptScore W3215857809C2776175482 @default.
- W3215857809 hasConceptScore W3215857809C41008148 @default.
- W3215857809 hasLocation W32158578091 @default.
- W3215857809 hasOpenAccess W3215857809 @default.
- W3215857809 hasPrimaryLocation W32158578091 @default.
- W3215857809 hasRelatedWork W2095054056 @default.
- W3215857809 hasRelatedWork W2765107853 @default.
- W3215857809 hasRelatedWork W2807706688 @default.
- W3215857809 hasRelatedWork W3092957620 @default.
- W3215857809 hasRelatedWork W3107474891 @default.
- W3215857809 hasRelatedWork W3202548321 @default.
- W3215857809 hasRelatedWork W3213996684 @default.
- W3215857809 hasRelatedWork W4286974328 @default.
- W3215857809 hasRelatedWork W4290058282 @default.
- W3215857809 hasRelatedWork W68817833 @default.
- W3215857809 isParatext "false" @default.
- W3215857809 isRetracted "false" @default.
- W3215857809 magId "3215857809" @default.
- W3215857809 workType "article" @default.