Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313332343> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4313332343 endingPage "634" @default.
- W4313332343 startingPage "621" @default.
- W4313332343 abstract "Abstract Bertalign is designed to improve sentence alignment accuracy for Chinese–English parallel corpora of literary texts. Aligning bilingual literary texts is not trivial, since most of the translation is interpretative and not based on 1-to-1 mappings between source and target sentences. Existing alignment methods highlight 1-to-1 links while having difficulty coping with 1-to-many and many-to-many alignments that are common in literary texts. To overcome the weaknesses of current approaches, we propose a novel two-step algorithm for bilingual sentence alignment. The first step finds the optimal paths for 1-to-1 alignments based on the top-k most semantically similar target sentences for each source sentence using the bidirectional encoder representations from transformer-based cross-lingual word embeddings. The second step relies on search paths found in the previous step to recover all valid alignments with more than one sentence on each side of the bilingual text. A comprehensive experiment was conducted on a newly built Chinese–English literary parallel corpus and a large-scale publicly available bilingual corpus of the Bible to compare the performance of Bertalign with five baseline systems: Gale-Church, Hunalign, Bleualign, Bleurtalign, and Vecalign. The results show that Bertalign achieves the highest accuracy in terms of F1 score on the two evaluation datasets than previous methods." @default.
- W4313332343 created "2023-01-06" @default.
- W4313332343 creator A5012738341 @default.
- W4313332343 creator A5020147975 @default.
- W4313332343 date "2022-12-29" @default.
- W4313332343 modified "2023-09-24" @default.
- W4313332343 title "Bertalign: Improved word embedding-based sentence alignment for Chinese–English parallel corpora of literary texts" @default.
- W4313332343 cites W1587731808 @default.
- W4313332343 cites W1768016410 @default.
- W4313332343 cites W2041532239 @default.
- W4313332343 cites W2074992284 @default.
- W4313332343 cites W2095503871 @default.
- W4313332343 cites W2141766660 @default.
- W4313332343 cites W2144994235 @default.
- W4313332343 cites W2154023657 @default.
- W4313332343 cites W2416264730 @default.
- W4313332343 cites W2522833918 @default.
- W4313332343 cites W2755616156 @default.
- W4313332343 cites W2912437182 @default.
- W4313332343 cites W2963680955 @default.
- W4313332343 cites W2963850840 @default.
- W4313332343 cites W2973088264 @default.
- W4313332343 cites W2990590620 @default.
- W4313332343 cites W2998702515 @default.
- W4313332343 cites W3198156935 @default.
- W4313332343 cites W3212032103 @default.
- W4313332343 cites W4211185538 @default.
- W4313332343 cites W4234178866 @default.
- W4313332343 cites W4240617655 @default.
- W4313332343 cites W4302388185 @default.
- W4313332343 cites W786625517 @default.
- W4313332343 doi "https://doi.org/10.1093/llc/fqac089" @default.
- W4313332343 hasPublicationYear "2022" @default.
- W4313332343 type Work @default.
- W4313332343 citedByCount "0" @default.
- W4313332343 crossrefType "journal-article" @default.
- W4313332343 hasAuthorship W4313332343A5012738341 @default.
- W4313332343 hasAuthorship W4313332343A5020147975 @default.
- W4313332343 hasConcept C111919701 @default.
- W4313332343 hasConcept C118505674 @default.
- W4313332343 hasConcept C120012220 @default.
- W4313332343 hasConcept C121332964 @default.
- W4313332343 hasConcept C138885662 @default.
- W4313332343 hasConcept C154945302 @default.
- W4313332343 hasConcept C165801399 @default.
- W4313332343 hasConcept C203005215 @default.
- W4313332343 hasConcept C204321447 @default.
- W4313332343 hasConcept C2777530160 @default.
- W4313332343 hasConcept C2779235283 @default.
- W4313332343 hasConcept C2985367798 @default.
- W4313332343 hasConcept C41008148 @default.
- W4313332343 hasConcept C41608201 @default.
- W4313332343 hasConcept C41895202 @default.
- W4313332343 hasConcept C62520636 @default.
- W4313332343 hasConcept C66322947 @default.
- W4313332343 hasConcept C90805587 @default.
- W4313332343 hasConceptScore W4313332343C111919701 @default.
- W4313332343 hasConceptScore W4313332343C118505674 @default.
- W4313332343 hasConceptScore W4313332343C120012220 @default.
- W4313332343 hasConceptScore W4313332343C121332964 @default.
- W4313332343 hasConceptScore W4313332343C138885662 @default.
- W4313332343 hasConceptScore W4313332343C154945302 @default.
- W4313332343 hasConceptScore W4313332343C165801399 @default.
- W4313332343 hasConceptScore W4313332343C203005215 @default.
- W4313332343 hasConceptScore W4313332343C204321447 @default.
- W4313332343 hasConceptScore W4313332343C2777530160 @default.
- W4313332343 hasConceptScore W4313332343C2779235283 @default.
- W4313332343 hasConceptScore W4313332343C2985367798 @default.
- W4313332343 hasConceptScore W4313332343C41008148 @default.
- W4313332343 hasConceptScore W4313332343C41608201 @default.
- W4313332343 hasConceptScore W4313332343C41895202 @default.
- W4313332343 hasConceptScore W4313332343C62520636 @default.
- W4313332343 hasConceptScore W4313332343C66322947 @default.
- W4313332343 hasConceptScore W4313332343C90805587 @default.
- W4313332343 hasIssue "2" @default.
- W4313332343 hasLocation W43133323431 @default.
- W4313332343 hasOpenAccess W4313332343 @default.
- W4313332343 hasPrimaryLocation W43133323431 @default.
- W4313332343 hasRelatedWork W1565387327 @default.
- W4313332343 hasRelatedWork W2004185987 @default.
- W4313332343 hasRelatedWork W2254397017 @default.
- W4313332343 hasRelatedWork W2762484717 @default.
- W4313332343 hasRelatedWork W3040377727 @default.
- W4313332343 hasRelatedWork W3119899169 @default.
- W4313332343 hasRelatedWork W3212418102 @default.
- W4313332343 hasRelatedWork W4299579390 @default.
- W4313332343 hasRelatedWork W4313332343 @default.
- W4313332343 hasRelatedWork W3141276838 @default.
- W4313332343 hasVolume "38" @default.
- W4313332343 isParatext "false" @default.
- W4313332343 isRetracted "false" @default.
- W4313332343 workType "article" @default.