Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285296929> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4285296929 abstract "What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages? We conduct a thorough empirical experiment in 10 languages to ascertain this, considering five factors: (1) the amount of fine-tuning data, (2) the noise in the fine-tuning data, (3) the amount of pre-training data in the model, (4) the impact of domain mismatch, and (5) language typology. In addition to yielding several heuristics, the experiments form a framework for evaluating the data sensitivities of machine translation systems. While mBART is robust to domain differences, its translations for unseen and typologically distant languages remain below 3.0 BLEU. In answer to our title’s question, mBART is not a low-resource panacea; we therefore encourage shifting the emphasis from new models to new data." @default.
- W4285296929 created "2022-07-14" @default.
- W4285296929 creator A5002889503 @default.
- W4285296929 creator A5003441670 @default.
- W4285296929 creator A5010051415 @default.
- W4285296929 creator A5013096057 @default.
- W4285296929 creator A5045036841 @default.
- W4285296929 creator A5046881440 @default.
- W4285296929 creator A5088658365 @default.
- W4285296929 date "2022-01-01" @default.
- W4285296929 modified "2023-09-26" @default.
- W4285296929 title "Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?" @default.
- W4285296929 doi "https://doi.org/10.18653/v1/2022.findings-acl.6" @default.
- W4285296929 hasPublicationYear "2022" @default.
- W4285296929 type Work @default.
- W4285296929 citedByCount "2" @default.
- W4285296929 countsByYear W42852969292022 @default.
- W4285296929 countsByYear W42852969292023 @default.
- W4285296929 crossrefType "proceedings-article" @default.
- W4285296929 hasAuthorship W4285296929A5002889503 @default.
- W4285296929 hasAuthorship W4285296929A5003441670 @default.
- W4285296929 hasAuthorship W4285296929A5010051415 @default.
- W4285296929 hasAuthorship W4285296929A5013096057 @default.
- W4285296929 hasAuthorship W4285296929A5045036841 @default.
- W4285296929 hasAuthorship W4285296929A5046881440 @default.
- W4285296929 hasAuthorship W4285296929A5088658365 @default.
- W4285296929 hasBestOaLocation W42852969291 @default.
- W4285296929 hasConcept C111919701 @default.
- W4285296929 hasConcept C127705205 @default.
- W4285296929 hasConcept C134306372 @default.
- W4285296929 hasConcept C137293760 @default.
- W4285296929 hasConcept C154945302 @default.
- W4285296929 hasConcept C166957645 @default.
- W4285296929 hasConcept C203005215 @default.
- W4285296929 hasConcept C204321447 @default.
- W4285296929 hasConcept C206345919 @default.
- W4285296929 hasConcept C2778112365 @default.
- W4285296929 hasConcept C28490314 @default.
- W4285296929 hasConcept C31258907 @default.
- W4285296929 hasConcept C33923547 @default.
- W4285296929 hasConcept C36503486 @default.
- W4285296929 hasConcept C41008148 @default.
- W4285296929 hasConcept C54355233 @default.
- W4285296929 hasConcept C75795011 @default.
- W4285296929 hasConcept C86803240 @default.
- W4285296929 hasConcept C95457728 @default.
- W4285296929 hasConceptScore W4285296929C111919701 @default.
- W4285296929 hasConceptScore W4285296929C127705205 @default.
- W4285296929 hasConceptScore W4285296929C134306372 @default.
- W4285296929 hasConceptScore W4285296929C137293760 @default.
- W4285296929 hasConceptScore W4285296929C154945302 @default.
- W4285296929 hasConceptScore W4285296929C166957645 @default.
- W4285296929 hasConceptScore W4285296929C203005215 @default.
- W4285296929 hasConceptScore W4285296929C204321447 @default.
- W4285296929 hasConceptScore W4285296929C206345919 @default.
- W4285296929 hasConceptScore W4285296929C2778112365 @default.
- W4285296929 hasConceptScore W4285296929C28490314 @default.
- W4285296929 hasConceptScore W4285296929C31258907 @default.
- W4285296929 hasConceptScore W4285296929C33923547 @default.
- W4285296929 hasConceptScore W4285296929C36503486 @default.
- W4285296929 hasConceptScore W4285296929C41008148 @default.
- W4285296929 hasConceptScore W4285296929C54355233 @default.
- W4285296929 hasConceptScore W4285296929C75795011 @default.
- W4285296929 hasConceptScore W4285296929C86803240 @default.
- W4285296929 hasConceptScore W4285296929C95457728 @default.
- W4285296929 hasLocation W42852969291 @default.
- W4285296929 hasLocation W42852969292 @default.
- W4285296929 hasOpenAccess W4285296929 @default.
- W4285296929 hasPrimaryLocation W42852969291 @default.
- W4285296929 hasRelatedWork W1484029852 @default.
- W4285296929 hasRelatedWork W1512718085 @default.
- W4285296929 hasRelatedWork W1569841287 @default.
- W4285296929 hasRelatedWork W2140460368 @default.
- W4285296929 hasRelatedWork W2167662847 @default.
- W4285296929 hasRelatedWork W3033942572 @default.
- W4285296929 hasRelatedWork W3198474835 @default.
- W4285296929 hasRelatedWork W4288804510 @default.
- W4285296929 hasRelatedWork W4379525811 @default.
- W4285296929 hasRelatedWork W2610387714 @default.
- W4285296929 isParatext "false" @default.
- W4285296929 isRetracted "false" @default.
- W4285296929 workType "article" @default.