Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213850607> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3213850607 abstract "Measuring the similarity score between a pair of sentences in different languages is the essential requisite for multilingual sentence embedding methods. Predicting the similarity score consists of two sub-tasks, which are monolingual similarity evaluation and multilingual sentence retrieval. However, conventional methods have mainly tackled only one of the sub-tasks and therefore showed biased performances. In this paper, we suggest a novel and strong method for multilingual sentence embedding, which shows performance improvement on both sub-tasks, consequently resulting in robust predictions of multilingual similarity scores. The suggested method consists of two parts: to learn semantic similarity of sentences in the pivot language and then to extend the learned semantic structure to different languages. To align semantic structures across different languages, we introduce a teacher-student network. The teacher network distills the knowledge of the pivot language to different languages of the student network. During the distillation, the parameters of the teacher network are updated with the slow-moving average. Together with the distillation and the parameter updating, the semantic structure of the student network can be directly aligned across different languages while preserving the ability to measure the semantic similarity. Thus, the multilingual training method drives performance improvement on multilingual similarity evaluation. The suggested model achieves the state-of-the-art performance on extended STS 2017 multilingual similarity evaluation as well as two sub-tasks, which are extended STS 2017 monolingual similarity evaluation and Tatoeba multilingual retrieval in 14 languages." @default.
- W3213850607 created "2021-11-22" @default.
- W3213850607 creator A5011022538 @default.
- W3213850607 creator A5044452894 @default.
- W3213850607 date "2021-01-01" @default.
- W3213850607 modified "2023-09-28" @default.
- W3213850607 title "Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding" @default.
- W3213850607 cites W1840435438 @default.
- W3213850607 cites W2099471712 @default.
- W3213850607 cites W2419539795 @default.
- W3213850607 cites W2572474373 @default.
- W3213850607 cites W2593864460 @default.
- W3213850607 cites W2749988060 @default.
- W3213850607 cites W2842511635 @default.
- W3213850607 cites W2949517790 @default.
- W3213850607 cites W2963250244 @default.
- W3213850607 cites W2963263347 @default.
- W3213850607 cites W2963341956 @default.
- W3213850607 cites W2963846996 @default.
- W3213850607 cites W2963918774 @default.
- W3213850607 cites W2965373594 @default.
- W3213850607 cites W2970620799 @default.
- W3213850607 cites W2977458338 @default.
- W3213850607 cites W3013840636 @default.
- W3213850607 cites W3034978746 @default.
- W3213850607 cites W3035390927 @default.
- W3213850607 cites W3035524453 @default.
- W3213850607 cites W3038033387 @default.
- W3213850607 cites W3100806282 @default.
- W3213850607 cites W3101821705 @default.
- W3213850607 cites W3104033643 @default.
- W3213850607 cites W3106428938 @default.
- W3213850607 cites W3172806051 @default.
- W3213850607 doi "https://doi.org/10.18653/v1/2021.findings-emnlp.153" @default.
- W3213850607 hasPublicationYear "2021" @default.
- W3213850607 type Work @default.
- W3213850607 sameAs 3213850607 @default.
- W3213850607 citedByCount "0" @default.
- W3213850607 crossrefType "proceedings-article" @default.
- W3213850607 hasAuthorship W3213850607A5011022538 @default.
- W3213850607 hasAuthorship W3213850607A5044452894 @default.
- W3213850607 hasBestOaLocation W32138506071 @default.
- W3213850607 hasConcept C103278499 @default.
- W3213850607 hasConcept C115961682 @default.
- W3213850607 hasConcept C130318100 @default.
- W3213850607 hasConcept C154945302 @default.
- W3213850607 hasConcept C204321447 @default.
- W3213850607 hasConcept C2777530160 @default.
- W3213850607 hasConcept C41008148 @default.
- W3213850607 hasConcept C41608201 @default.
- W3213850607 hasConceptScore W3213850607C103278499 @default.
- W3213850607 hasConceptScore W3213850607C115961682 @default.
- W3213850607 hasConceptScore W3213850607C130318100 @default.
- W3213850607 hasConceptScore W3213850607C154945302 @default.
- W3213850607 hasConceptScore W3213850607C204321447 @default.
- W3213850607 hasConceptScore W3213850607C2777530160 @default.
- W3213850607 hasConceptScore W3213850607C41008148 @default.
- W3213850607 hasConceptScore W3213850607C41608201 @default.
- W3213850607 hasLocation W32138506071 @default.
- W3213850607 hasOpenAccess W3213850607 @default.
- W3213850607 hasPrimaryLocation W32138506071 @default.
- W3213850607 hasRelatedWork W1997312918 @default.
- W3213850607 hasRelatedWork W2047828095 @default.
- W3213850607 hasRelatedWork W2116838603 @default.
- W3213850607 hasRelatedWork W2252122760 @default.
- W3213850607 hasRelatedWork W2365659184 @default.
- W3213850607 hasRelatedWork W2766760871 @default.
- W3213850607 hasRelatedWork W2899468685 @default.
- W3213850607 hasRelatedWork W3078371441 @default.
- W3213850607 hasRelatedWork W4312046383 @default.
- W3213850607 hasRelatedWork W78638240 @default.
- W3213850607 isParatext "false" @default.
- W3213850607 isRetracted "false" @default.
- W3213850607 magId "3213850607" @default.
- W3213850607 workType "article" @default.