Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377191776> ?p ?o ?g. }
- W4377191776 endingPage "131" @default.
- W4377191776 startingPage "115" @default.
- W4377191776 abstract "Named Entity Recognition (NER) is a key step in the creation of structured data from digitised historical documents. Traditional NER approaches deal with flat named entities, whereas entities are often nested. For example, a postal address might contain a street name and a number. This work compares three nested NER approaches, including two state-of-the-art approaches using Transformer-based architectures. We introduce a new Transformer-based approach based on joint labelling and semantic weighting of errors, evaluated on a collection of 19th-century Paris trade directories. We evaluate approaches regarding the impact of supervised fine-tuning, unsupervised pre-training with noisy texts, and variation of IOB tagging formats. Our results show that while nested NER approaches enable extracting structured data directly, they do not benefit from the extra knowledge provided during training and reach a performance similar to the base approach on flat entities. Even though all 3 approaches perform well in terms of F1-scores, joint labelling is most suitable for hierarchically structured data. Finally, our experiments reveal the superiority of the IO tagging format on such data." @default.
- W4377191776 created "2023-05-22" @default.
- W4377191776 creator A5009127540 @default.
- W4377191776 creator A5016724318 @default.
- W4377191776 creator A5059793245 @default.
- W4377191776 creator A5068764363 @default.
- W4377191776 creator A5075259913 @default.
- W4377191776 date "2023-01-01" @default.
- W4377191776 modified "2023-10-14" @default.
- W4377191776 title "A Benchmark of Nested Named Entity Recognition Approaches in Historical Structured Documents" @default.
- W4377191776 cites W1981797826 @default.
- W4377191776 cites W2020278455 @default.
- W4377191776 cites W2047477415 @default.
- W4377191776 cites W2804221886 @default.
- W4377191776 cites W2963750238 @default.
- W4377191776 cites W2971019153 @default.
- W4377191776 cites W2986154550 @default.
- W4377191776 cites W2990235080 @default.
- W4377191776 cites W3011594683 @default.
- W4377191776 cites W3035406632 @default.
- W4377191776 cites W3055666129 @default.
- W4377191776 cites W3102295886 @default.
- W4377191776 cites W3175437227 @default.
- W4377191776 cites W3191607794 @default.
- W4377191776 cites W3199081815 @default.
- W4377191776 cites W3199216253 @default.
- W4377191776 cites W3208962647 @default.
- W4377191776 cites W4206505934 @default.
- W4377191776 cites W4221025428 @default.
- W4377191776 cites W4283361265 @default.
- W4377191776 doi "https://doi.org/10.1007/978-3-031-41682-8_8" @default.
- W4377191776 hasPublicationYear "2023" @default.
- W4377191776 type Work @default.
- W4377191776 citedByCount "0" @default.
- W4377191776 crossrefType "book-chapter" @default.
- W4377191776 hasAuthorship W4377191776A5009127540 @default.
- W4377191776 hasAuthorship W4377191776A5016724318 @default.
- W4377191776 hasAuthorship W4377191776A5059793245 @default.
- W4377191776 hasAuthorship W4377191776A5068764363 @default.
- W4377191776 hasAuthorship W4377191776A5075259913 @default.
- W4377191776 hasBestOaLocation W43771917762 @default.
- W4377191776 hasConcept C121332964 @default.
- W4377191776 hasConcept C124101348 @default.
- W4377191776 hasConcept C126838900 @default.
- W4377191776 hasConcept C13280743 @default.
- W4377191776 hasConcept C154945302 @default.
- W4377191776 hasConcept C162324750 @default.
- W4377191776 hasConcept C165801399 @default.
- W4377191776 hasConcept C183115368 @default.
- W4377191776 hasConcept C185798385 @default.
- W4377191776 hasConcept C187736073 @default.
- W4377191776 hasConcept C204321447 @default.
- W4377191776 hasConcept C205649164 @default.
- W4377191776 hasConcept C23123220 @default.
- W4377191776 hasConcept C2779135771 @default.
- W4377191776 hasConcept C2780451532 @default.
- W4377191776 hasConcept C41008148 @default.
- W4377191776 hasConcept C4554734 @default.
- W4377191776 hasConcept C62520636 @default.
- W4377191776 hasConcept C66322947 @default.
- W4377191776 hasConcept C71924100 @default.
- W4377191776 hasConcept C96711827 @default.
- W4377191776 hasConceptScore W4377191776C121332964 @default.
- W4377191776 hasConceptScore W4377191776C124101348 @default.
- W4377191776 hasConceptScore W4377191776C126838900 @default.
- W4377191776 hasConceptScore W4377191776C13280743 @default.
- W4377191776 hasConceptScore W4377191776C154945302 @default.
- W4377191776 hasConceptScore W4377191776C162324750 @default.
- W4377191776 hasConceptScore W4377191776C165801399 @default.
- W4377191776 hasConceptScore W4377191776C183115368 @default.
- W4377191776 hasConceptScore W4377191776C185798385 @default.
- W4377191776 hasConceptScore W4377191776C187736073 @default.
- W4377191776 hasConceptScore W4377191776C204321447 @default.
- W4377191776 hasConceptScore W4377191776C205649164 @default.
- W4377191776 hasConceptScore W4377191776C23123220 @default.
- W4377191776 hasConceptScore W4377191776C2779135771 @default.
- W4377191776 hasConceptScore W4377191776C2780451532 @default.
- W4377191776 hasConceptScore W4377191776C41008148 @default.
- W4377191776 hasConceptScore W4377191776C4554734 @default.
- W4377191776 hasConceptScore W4377191776C62520636 @default.
- W4377191776 hasConceptScore W4377191776C66322947 @default.
- W4377191776 hasConceptScore W4377191776C71924100 @default.
- W4377191776 hasConceptScore W4377191776C96711827 @default.
- W4377191776 hasLocation W43771917761 @default.
- W4377191776 hasLocation W43771917762 @default.
- W4377191776 hasLocation W43771917763 @default.
- W4377191776 hasOpenAccess W4377191776 @default.
- W4377191776 hasPrimaryLocation W43771917761 @default.
- W4377191776 hasRelatedWork W1884363728 @default.
- W4377191776 hasRelatedWork W2520117834 @default.
- W4377191776 hasRelatedWork W2593907245 @default.
- W4377191776 hasRelatedWork W2883921205 @default.
- W4377191776 hasRelatedWork W3000685722 @default.
- W4377191776 hasRelatedWork W3133906981 @default.
- W4377191776 hasRelatedWork W3198729192 @default.
- W4377191776 hasRelatedWork W4255258373 @default.
- W4377191776 hasRelatedWork W4313162113 @default.
- W4377191776 hasRelatedWork W2186562580 @default.