Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309778912> ?p ?o ?g. }
- W4309778912 endingPage "119274" @default.
- W4309778912 startingPage "119274" @default.
- W4309778912 abstract "Information extraction (IE) is a vital step of digitization that reduces paperwork in offices. However, the adaptation of common IE systems to actual business cases faces two issues. First, the number of training samples is small (i.e. 100–200 examples). Second, span extraction models based on question answering formulation require a long time for training and inference. To overcome these issues, we introduce a new query-based model for the extraction of information from business documents. For data limitation, the model employs transfer learning which adapts the knowledge of pre-trained language models (i.e. BERT) to specific domains. To do that, we design a new CNN layer for the adaptation of the model to specific domains. For the speed, different from the encoding of normal span extraction methods (BERT-QA), the proposed model encodes short tags and context documents in two channels in parallel, which speeds up training and inference time. Information from short tags is fused with context documents learned from CNN by using attention to predict start and end positions of extracted spans. Promising results on five domain-specific datasets in English and Japanese indicate that the proposed model produces high-quality outputs and can be applied for business scenarios." @default.
- W4309778912 created "2022-11-29" @default.
- W4309778912 creator A5010175697 @default.
- W4309778912 creator A5027862708 @default.
- W4309778912 creator A5068673769 @default.
- W4309778912 date "2023-04-01" @default.
- W4309778912 modified "2023-09-27" @default.
- W4309778912 title "Gain more with less: Extracting information from business documents with small data" @default.
- W4309778912 cites W1529731474 @default.
- W4309778912 cites W1902237438 @default.
- W4309778912 cites W2144578941 @default.
- W4309778912 cites W2148317291 @default.
- W4309778912 cites W2194187530 @default.
- W4309778912 cites W2250539671 @default.
- W4309778912 cites W2251239360 @default.
- W4309778912 cites W2251913848 @default.
- W4309778912 cites W2296283641 @default.
- W4309778912 cites W2557764419 @default.
- W4309778912 cites W2804221886 @default.
- W4309778912 cites W2912924812 @default.
- W4309778912 cites W2955710688 @default.
- W4309778912 cites W2962718483 @default.
- W4309778912 cites W2963412182 @default.
- W4309778912 cites W2963748441 @default.
- W4309778912 cites W2963967365 @default.
- W4309778912 cites W2964330146 @default.
- W4309778912 cites W3034862440 @default.
- W4309778912 cites W3035625205 @default.
- W4309778912 cites W3093598662 @default.
- W4309778912 cites W3106904896 @default.
- W4309778912 cites W3132591435 @default.
- W4309778912 cites W3164872774 @default.
- W4309778912 cites W3217231121 @default.
- W4309778912 doi "https://doi.org/10.1016/j.eswa.2022.119274" @default.
- W4309778912 hasPublicationYear "2023" @default.
- W4309778912 type Work @default.
- W4309778912 citedByCount "0" @default.
- W4309778912 crossrefType "journal-article" @default.
- W4309778912 hasAuthorship W4309778912A5010175697 @default.
- W4309778912 hasAuthorship W4309778912A5027862708 @default.
- W4309778912 hasAuthorship W4309778912A5068673769 @default.
- W4309778912 hasConcept C111472728 @default.
- W4309778912 hasConcept C119857082 @default.
- W4309778912 hasConcept C120665830 @default.
- W4309778912 hasConcept C121332964 @default.
- W4309778912 hasConcept C124101348 @default.
- W4309778912 hasConcept C134306372 @default.
- W4309778912 hasConcept C138885662 @default.
- W4309778912 hasConcept C139807058 @default.
- W4309778912 hasConcept C151730666 @default.
- W4309778912 hasConcept C154945302 @default.
- W4309778912 hasConcept C162324750 @default.
- W4309778912 hasConcept C187736073 @default.
- W4309778912 hasConcept C195807954 @default.
- W4309778912 hasConcept C204321447 @default.
- W4309778912 hasConcept C23123220 @default.
- W4309778912 hasConcept C2776214188 @default.
- W4309778912 hasConcept C2776434776 @default.
- W4309778912 hasConcept C2779135771 @default.
- W4309778912 hasConcept C2779343474 @default.
- W4309778912 hasConcept C2779530757 @default.
- W4309778912 hasConcept C2780451532 @default.
- W4309778912 hasConcept C33923547 @default.
- W4309778912 hasConcept C36503486 @default.
- W4309778912 hasConcept C41008148 @default.
- W4309778912 hasConcept C86803240 @default.
- W4309778912 hasConcept C95623464 @default.
- W4309778912 hasConceptScore W4309778912C111472728 @default.
- W4309778912 hasConceptScore W4309778912C119857082 @default.
- W4309778912 hasConceptScore W4309778912C120665830 @default.
- W4309778912 hasConceptScore W4309778912C121332964 @default.
- W4309778912 hasConceptScore W4309778912C124101348 @default.
- W4309778912 hasConceptScore W4309778912C134306372 @default.
- W4309778912 hasConceptScore W4309778912C138885662 @default.
- W4309778912 hasConceptScore W4309778912C139807058 @default.
- W4309778912 hasConceptScore W4309778912C151730666 @default.
- W4309778912 hasConceptScore W4309778912C154945302 @default.
- W4309778912 hasConceptScore W4309778912C162324750 @default.
- W4309778912 hasConceptScore W4309778912C187736073 @default.
- W4309778912 hasConceptScore W4309778912C195807954 @default.
- W4309778912 hasConceptScore W4309778912C204321447 @default.
- W4309778912 hasConceptScore W4309778912C23123220 @default.
- W4309778912 hasConceptScore W4309778912C2776214188 @default.
- W4309778912 hasConceptScore W4309778912C2776434776 @default.
- W4309778912 hasConceptScore W4309778912C2779135771 @default.
- W4309778912 hasConceptScore W4309778912C2779343474 @default.
- W4309778912 hasConceptScore W4309778912C2779530757 @default.
- W4309778912 hasConceptScore W4309778912C2780451532 @default.
- W4309778912 hasConceptScore W4309778912C33923547 @default.
- W4309778912 hasConceptScore W4309778912C36503486 @default.
- W4309778912 hasConceptScore W4309778912C41008148 @default.
- W4309778912 hasConceptScore W4309778912C86803240 @default.
- W4309778912 hasConceptScore W4309778912C95623464 @default.
- W4309778912 hasLocation W43097789121 @default.
- W4309778912 hasOpenAccess W4309778912 @default.
- W4309778912 hasPrimaryLocation W43097789121 @default.
- W4309778912 hasRelatedWork W1142185071 @default.
- W4309778912 hasRelatedWork W147166030 @default.