Matches in SemOpenAlex for { <https://semopenalex.org/work/W19862471> ?p ?o ?g. }
- W19862471 endingPage "29" @default.
- W19862471 startingPage "21" @default.
- W19862471 abstract "We present a new approach to named-entity recognition that jointly learns to identify named-entities in parallel text. The system generates seed candidates through local, cross-language edit likelihood and then bootstraps to make broad predictions across both languages, optimizing combined contextual, word-shape and alignment models. It is completely unsupervised, with no manually labeled items, no external resources, only using parallel text that does not need to be easily alignable. The results are strong, with F > 0.85 for purely unsupervised named-entity recognition across languages, compared to just F = 0.35 on the same data for supervised cross-domain named-entity recognition within a language. A combination of unsupervised and supervised methods increases the accuracy to F = 0.88. We conclude that we have found a viable new strategy for unsupervised named-entity recognition across low-resource languages and for domain-adaptation within high-resource languages." @default.
- W19862471 created "2016-06-24" @default.
- W19862471 creator A5015817742 @default.
- W19862471 creator A5046006076 @default.
- W19862471 date "2012-07-12" @default.
- W19862471 modified "2023-09-25" @default.
- W19862471 title "Accurate Unsupervised Joint Named-Entity Extraction from Unaligned Parallel Text" @default.
- W19862471 cites W1533057952 @default.
- W19862471 cites W1586961776 @default.
- W19862471 cites W179918679 @default.
- W19862471 cites W180782768 @default.
- W19862471 cites W1870418615 @default.
- W19862471 cites W2016630033 @default.
- W19862471 cites W2085615197 @default.
- W19862471 cites W2088271224 @default.
- W19862471 cites W2096648470 @default.
- W19862471 cites W2099370490 @default.
- W19862471 cites W2114879013 @default.
- W19862471 cites W2120349760 @default.
- W19862471 cites W2124807415 @default.
- W19862471 cites W2140037211 @default.
- W19862471 cites W2143954309 @default.
- W19862471 cites W2144578941 @default.
- W19862471 cites W2145956377 @default.
- W19862471 cites W2151976760 @default.
- W19862471 cites W2552843868 @default.
- W19862471 cites W2895810819 @default.
- W19862471 cites W2915429162 @default.
- W19862471 cites W345025638 @default.
- W19862471 hasPublicationYear "2012" @default.
- W19862471 type Work @default.
- W19862471 sameAs 19862471 @default.
- W19862471 citedByCount "7" @default.
- W19862471 countsByYear W198624712012 @default.
- W19862471 countsByYear W198624712013 @default.
- W19862471 countsByYear W198624712014 @default.
- W19862471 countsByYear W198624712018 @default.
- W19862471 countsByYear W198624712019 @default.
- W19862471 crossrefType "proceedings-article" @default.
- W19862471 hasAuthorship W19862471A5015817742 @default.
- W19862471 hasAuthorship W19862471A5046006076 @default.
- W19862471 hasConcept C134306372 @default.
- W19862471 hasConcept C138885662 @default.
- W19862471 hasConcept C154945302 @default.
- W19862471 hasConcept C162324750 @default.
- W19862471 hasConcept C187736073 @default.
- W19862471 hasConcept C195807954 @default.
- W19862471 hasConcept C204321447 @default.
- W19862471 hasConcept C2776434776 @default.
- W19862471 hasConcept C2777889803 @default.
- W19862471 hasConcept C2779135771 @default.
- W19862471 hasConcept C2780451532 @default.
- W19862471 hasConcept C33923547 @default.
- W19862471 hasConcept C36503486 @default.
- W19862471 hasConcept C41008148 @default.
- W19862471 hasConcept C41895202 @default.
- W19862471 hasConcept C4554734 @default.
- W19862471 hasConcept C8038995 @default.
- W19862471 hasConcept C90805587 @default.
- W19862471 hasConcept C95623464 @default.
- W19862471 hasConcept C96711827 @default.
- W19862471 hasConceptScore W19862471C134306372 @default.
- W19862471 hasConceptScore W19862471C138885662 @default.
- W19862471 hasConceptScore W19862471C154945302 @default.
- W19862471 hasConceptScore W19862471C162324750 @default.
- W19862471 hasConceptScore W19862471C187736073 @default.
- W19862471 hasConceptScore W19862471C195807954 @default.
- W19862471 hasConceptScore W19862471C204321447 @default.
- W19862471 hasConceptScore W19862471C2776434776 @default.
- W19862471 hasConceptScore W19862471C2777889803 @default.
- W19862471 hasConceptScore W19862471C2779135771 @default.
- W19862471 hasConceptScore W19862471C2780451532 @default.
- W19862471 hasConceptScore W19862471C33923547 @default.
- W19862471 hasConceptScore W19862471C36503486 @default.
- W19862471 hasConceptScore W19862471C41008148 @default.
- W19862471 hasConceptScore W19862471C41895202 @default.
- W19862471 hasConceptScore W19862471C4554734 @default.
- W19862471 hasConceptScore W19862471C8038995 @default.
- W19862471 hasConceptScore W19862471C90805587 @default.
- W19862471 hasConceptScore W19862471C95623464 @default.
- W19862471 hasConceptScore W19862471C96711827 @default.
- W19862471 hasLocation W198624711 @default.
- W19862471 hasOpenAccess W19862471 @default.
- W19862471 hasPrimaryLocation W198624711 @default.
- W19862471 hasRelatedWork W2042162260 @default.
- W19862471 hasRelatedWork W2087923637 @default.
- W19862471 hasRelatedWork W2148540243 @default.
- W19862471 hasRelatedWork W2152346074 @default.
- W19862471 hasRelatedWork W2164119735 @default.
- W19862471 hasRelatedWork W2396200542 @default.
- W19862471 hasRelatedWork W2734693922 @default.
- W19862471 hasRelatedWork W2740465560 @default.
- W19862471 hasRelatedWork W2756894272 @default.
- W19862471 hasRelatedWork W2773655913 @default.
- W19862471 hasRelatedWork W2791388596 @default.
- W19862471 hasRelatedWork W2799125718 @default.
- W19862471 hasRelatedWork W2949240516 @default.
- W19862471 hasRelatedWork W2972157485 @default.