Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366274340> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4366274340 endingPage "18" @default.
- W4366274340 startingPage "1" @default.
- W4366274340 abstract "Cross-lingual sentence embedding’s goal is mapping sentences with similar semantics but in different languages close together and dissimilar sentences farther apart in the representation space. It is the basis of many downstream tasks such as cross-lingual document matching and cross-lingual summary extraction. At present, the works of cross-lingual sentence embedding tasks mainly focus on languages with large-scale corpus. But low-resource languages such as Chinese-Vietnamese are short of sentence-level parallel corpora and clear cross-lingual monitoring signals, and these works on low-resource languages have poor performances. Therefore, we propose a cross-lingual sentence embedding method based on contrastive learning and effectively fine-tune powerful pretraining mode by constructing sentence-level positive and negative samples to avoid the catastrophic forgetting problem of the traditional fine-tuning pre-trained model based only on small-scale aligned positive samples. First, we construct positive and negative examples by taking parallel Chinese Vietnamese sentences as positive examples and non-parallel sentences as negative examples. Second, we construct a siamese network to get contrastive loss by inputting positive and negative samples and fine-tuning our model. The experimental results show that our method can effectively improve the semantic alignment accuracy of cross-lingual sentence embedding in Chinese and Vietnamese contexts." @default.
- W4366274340 created "2023-04-20" @default.
- W4366274340 creator A5000922713 @default.
- W4366274340 creator A5059833928 @default.
- W4366274340 creator A5067563332 @default.
- W4366274340 creator A5070860104 @default.
- W4366274340 creator A5087885961 @default.
- W4366274340 date "2023-06-16" @default.
- W4366274340 modified "2023-10-16" @default.
- W4366274340 title "Cross-lingual Sentence Embedding for Low-resource Chinese-Vietnamese Based on Contrastive Learning" @default.
- W4366274340 cites W2171590421 @default.
- W4366274340 cites W2948947170 @default.
- W4366274340 cites W2950342398 @default.
- W4366274340 cites W2952638691 @default.
- W4366274340 cites W2963341956 @default.
- W4366274340 cites W2970641574 @default.
- W4366274340 cites W2973088264 @default.
- W4366274340 cites W3035390927 @default.
- W4366274340 cites W3103490574 @default.
- W4366274340 cites W3156194904 @default.
- W4366274340 cites W3175689281 @default.
- W4366274340 cites W4224313754 @default.
- W4366274340 doi "https://doi.org/10.1145/3589341" @default.
- W4366274340 hasPublicationYear "2023" @default.
- W4366274340 type Work @default.
- W4366274340 citedByCount "0" @default.
- W4366274340 crossrefType "journal-article" @default.
- W4366274340 hasAuthorship W4366274340A5000922713 @default.
- W4366274340 hasAuthorship W4366274340A5059833928 @default.
- W4366274340 hasAuthorship W4366274340A5067563332 @default.
- W4366274340 hasAuthorship W4366274340A5070860104 @default.
- W4366274340 hasAuthorship W4366274340A5087885961 @default.
- W4366274340 hasBestOaLocation W43662743401 @default.
- W4366274340 hasConcept C103621254 @default.
- W4366274340 hasConcept C120665830 @default.
- W4366274340 hasConcept C121332964 @default.
- W4366274340 hasConcept C138885662 @default.
- W4366274340 hasConcept C154945302 @default.
- W4366274340 hasConcept C192209626 @default.
- W4366274340 hasConcept C199360897 @default.
- W4366274340 hasConcept C204321447 @default.
- W4366274340 hasConcept C2777530160 @default.
- W4366274340 hasConcept C2780801425 @default.
- W4366274340 hasConcept C41008148 @default.
- W4366274340 hasConcept C41608201 @default.
- W4366274340 hasConcept C41895202 @default.
- W4366274340 hasConceptScore W4366274340C103621254 @default.
- W4366274340 hasConceptScore W4366274340C120665830 @default.
- W4366274340 hasConceptScore W4366274340C121332964 @default.
- W4366274340 hasConceptScore W4366274340C138885662 @default.
- W4366274340 hasConceptScore W4366274340C154945302 @default.
- W4366274340 hasConceptScore W4366274340C192209626 @default.
- W4366274340 hasConceptScore W4366274340C199360897 @default.
- W4366274340 hasConceptScore W4366274340C204321447 @default.
- W4366274340 hasConceptScore W4366274340C2777530160 @default.
- W4366274340 hasConceptScore W4366274340C2780801425 @default.
- W4366274340 hasConceptScore W4366274340C41008148 @default.
- W4366274340 hasConceptScore W4366274340C41608201 @default.
- W4366274340 hasConceptScore W4366274340C41895202 @default.
- W4366274340 hasFunder F4320321001 @default.
- W4366274340 hasIssue "6" @default.
- W4366274340 hasLocation W43662743401 @default.
- W4366274340 hasOpenAccess W4366274340 @default.
- W4366274340 hasPrimaryLocation W43662743401 @default.
- W4366274340 hasRelatedWork W1567338489 @default.
- W4366274340 hasRelatedWork W159132833 @default.
- W4366274340 hasRelatedWork W1978971213 @default.
- W4366274340 hasRelatedWork W2002261357 @default.
- W4366274340 hasRelatedWork W2101865203 @default.
- W4366274340 hasRelatedWork W2755089449 @default.
- W4366274340 hasRelatedWork W2983766097 @default.
- W4366274340 hasRelatedWork W3108520605 @default.
- W4366274340 hasRelatedWork W4224925590 @default.
- W4366274340 hasRelatedWork W4312046383 @default.
- W4366274340 hasVolume "22" @default.
- W4366274340 isParatext "false" @default.
- W4366274340 isRetracted "false" @default.
- W4366274340 workType "article" @default.