Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226075101> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4226075101 abstract "Multilingual evaluation benchmarks usually contain limited high-resource languages and do not test models for specific linguistic capabilities. CheckList is a template-based evaluation approach that tests models for specific capabilities. The CheckList template creation process requires native speakers, posing a challenge in scaling to hundreds of languages. In this work, we explore multiple approaches to generate Multilingual CheckLists. We device an algorithm - Template Extraction Algorithm (TEA) for automatically extracting target language CheckList templates from machine translated instances of a source language templates. We compare the TEA CheckLists with CheckLists created with different levels of human intervention. We further introduce metrics along the dimensions of cost, diversity, utility, and correctness to compare the CheckLists. We thoroughly analyze different approaches to creating CheckLists in Hindi. Furthermore, we experiment with 9 more different languages. We find that TEA followed by human verification is ideal for scaling Checklist-based evaluation to multiple languages while TEA gives a good estimates of model performance." @default.
- W4226075101 created "2022-05-05" @default.
- W4226075101 creator A5005513786 @default.
- W4226075101 creator A5006779728 @default.
- W4226075101 creator A5008944385 @default.
- W4226075101 creator A5049487173 @default.
- W4226075101 creator A5061503417 @default.
- W4226075101 creator A5071844229 @default.
- W4226075101 creator A5072668854 @default.
- W4226075101 date "2022-03-24" @default.
- W4226075101 modified "2023-10-14" @default.
- W4226075101 title "Multilingual CheckList: Generation and Evaluation" @default.
- W4226075101 doi "https://doi.org/10.48550/arxiv.2203.12865" @default.
- W4226075101 hasPublicationYear "2022" @default.
- W4226075101 type Work @default.
- W4226075101 citedByCount "0" @default.
- W4226075101 crossrefType "posted-content" @default.
- W4226075101 hasAuthorship W4226075101A5005513786 @default.
- W4226075101 hasAuthorship W4226075101A5006779728 @default.
- W4226075101 hasAuthorship W4226075101A5008944385 @default.
- W4226075101 hasAuthorship W4226075101A5049487173 @default.
- W4226075101 hasAuthorship W4226075101A5061503417 @default.
- W4226075101 hasAuthorship W4226075101A5071844229 @default.
- W4226075101 hasAuthorship W4226075101A5072668854 @default.
- W4226075101 hasBestOaLocation W42260751011 @default.
- W4226075101 hasConcept C154945302 @default.
- W4226075101 hasConcept C15744967 @default.
- W4226075101 hasConcept C180747234 @default.
- W4226075101 hasConcept C199360897 @default.
- W4226075101 hasConcept C204321447 @default.
- W4226075101 hasConcept C2779356329 @default.
- W4226075101 hasConcept C41008148 @default.
- W4226075101 hasConcept C55439883 @default.
- W4226075101 hasConcept C82714645 @default.
- W4226075101 hasConcept C98045186 @default.
- W4226075101 hasConceptScore W4226075101C154945302 @default.
- W4226075101 hasConceptScore W4226075101C15744967 @default.
- W4226075101 hasConceptScore W4226075101C180747234 @default.
- W4226075101 hasConceptScore W4226075101C199360897 @default.
- W4226075101 hasConceptScore W4226075101C204321447 @default.
- W4226075101 hasConceptScore W4226075101C2779356329 @default.
- W4226075101 hasConceptScore W4226075101C41008148 @default.
- W4226075101 hasConceptScore W4226075101C55439883 @default.
- W4226075101 hasConceptScore W4226075101C82714645 @default.
- W4226075101 hasConceptScore W4226075101C98045186 @default.
- W4226075101 hasLocation W42260751011 @default.
- W4226075101 hasOpenAccess W4226075101 @default.
- W4226075101 hasPrimaryLocation W42260751011 @default.
- W4226075101 hasRelatedWork W1516169988 @default.
- W4226075101 hasRelatedWork W1517743118 @default.
- W4226075101 hasRelatedWork W1567338489 @default.
- W4226075101 hasRelatedWork W1985198438 @default.
- W4226075101 hasRelatedWork W2024218563 @default.
- W4226075101 hasRelatedWork W2072806201 @default.
- W4226075101 hasRelatedWork W2363881323 @default.
- W4226075101 hasRelatedWork W2365918773 @default.
- W4226075101 hasRelatedWork W2965845133 @default.
- W4226075101 hasRelatedWork W4226075101 @default.
- W4226075101 isParatext "false" @default.
- W4226075101 isRetracted "false" @default.
- W4226075101 workType "article" @default.