FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379519265> ?p ?o ?g. }

• W4379519265 endingPage "23" @default.
• W4379519265 startingPage "1" @default.
• W4379519265 abstract "Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive performances in NER, many domain-specific NER applications still call for a substantial amount of labeled data. Active learning (AL), a general framework for the label acquisition problem, has been used for NER tasks to minimize the annotation cost without sacrificing model performance. However, the heavily imbalanced class distribution of tokens introduces challenges in designing effective AL querying methods for NER. We propose several AL sentence query evaluation functions that pay more attention to potential positive tokens, and evaluate these proposed functions with both sentence-based and token-based cost evaluation strategies. We also propose a better data-driven normalization approach to penalize sentences that are too long or too short. Our experiments on three datasets from different domains reveal that the proposed approach reduces the number of annotated tokens while achieving better or comparable prediction performance with conventional methods." @default.
• W4379519265 created "2023-06-07" @default.
• W4379519265 creator A5035084467 @default.
• W4379519265 creator A5051657734 @default.
• W4379519265 creator A5071697234 @default.
• W4379519265 creator A5092098096 @default.
• W4379519265 date "2023-06-06" @default.
• W4379519265 modified "2023-09-26" @default.
• W4379519265 title "Focusing on potential named entities during active label acquisition" @default.
• W4379519265 cites W151377110 @default.
• W4379519265 cites W1513874326 @default.
• W4379519265 cites W1580375566 @default.
• W4379519265 cites W1956471287 @default.
• W4379519265 cites W1995875735 @default.
• W4379519265 cites W2010588484 @default.
• W4379519265 cites W2051434435 @default.
• W4379519265 cites W2055617685 @default.
• W4379519265 cites W2074064986 @default.
• W4379519265 cites W2095729244 @default.
• W4379519265 cites W2113152670 @default.
• W4379519265 cites W2117763124 @default.
• W4379519265 cites W2132038179 @default.
• W4379519265 cites W2144182447 @default.
• W4379519265 cites W2144452292 @default.
• W4379519265 cites W2144578941 @default.
• W4379519265 cites W2154250549 @default.
• W4379519265 cites W2169099542 @default.
• W4379519265 cites W2171671120 @default.
• W4379519265 cites W2180566385 @default.
• W4379519265 cites W2252069213 @default.
• W4379519265 cites W2294798173 @default.
• W4379519265 cites W2346452181 @default.
• W4379519265 cites W2509700522 @default.
• W4379519265 cites W2785787385 @default.
• W4379519265 cites W2911489562 @default.
• W4379519265 cites W2963716420 @default.
• W4379519265 cites W2970352191 @default.
• W4379519265 cites W3035858791 @default.
• W4379519265 cites W3098466758 @default.
• W4379519265 cites W4206797693 @default.
• W4379519265 doi "https://doi.org/10.1017/s1351324923000165" @default.
• W4379519265 hasPublicationYear "2023" @default.
• W4379519265 type Work @default.
• W4379519265 citedByCount "0" @default.
• W4379519265 crossrefType "journal-article" @default.
• W4379519265 hasAuthorship W4379519265A5035084467 @default.
• W4379519265 hasAuthorship W4379519265A5051657734 @default.
• W4379519265 hasAuthorship W4379519265A5071697234 @default.
• W4379519265 hasAuthorship W4379519265A5092098096 @default.
• W4379519265 hasBestOaLocation W43795192651 @default.
• W4379519265 hasConcept C119857082 @default.
• W4379519265 hasConcept C136886441 @default.
• W4379519265 hasConcept C144024400 @default.
• W4379519265 hasConcept C154945302 @default.
• W4379519265 hasConcept C162324750 @default.
• W4379519265 hasConcept C187736073 @default.
• W4379519265 hasConcept C19165224 @default.
• W4379519265 hasConcept C204321447 @default.
• W4379519265 hasConcept C2776145971 @default.
• W4379519265 hasConcept C2776321320 @default.
• W4379519265 hasConcept C2777530160 @default.
• W4379519265 hasConcept C2777889803 @default.
• W4379519265 hasConcept C2779135771 @default.
• W4379519265 hasConcept C2780451532 @default.
• W4379519265 hasConcept C38652104 @default.
• W4379519265 hasConcept C41008148 @default.
• W4379519265 hasConcept C48145219 @default.
• W4379519265 hasConceptScore W4379519265C119857082 @default.
• W4379519265 hasConceptScore W4379519265C136886441 @default.
• W4379519265 hasConceptScore W4379519265C144024400 @default.
• W4379519265 hasConceptScore W4379519265C154945302 @default.
• W4379519265 hasConceptScore W4379519265C162324750 @default.
• W4379519265 hasConceptScore W4379519265C187736073 @default.
• W4379519265 hasConceptScore W4379519265C19165224 @default.
• W4379519265 hasConceptScore W4379519265C204321447 @default.
• W4379519265 hasConceptScore W4379519265C2776145971 @default.
• W4379519265 hasConceptScore W4379519265C2776321320 @default.
• W4379519265 hasConceptScore W4379519265C2777530160 @default.
• W4379519265 hasConceptScore W4379519265C2777889803 @default.
• W4379519265 hasConceptScore W4379519265C2779135771 @default.
• W4379519265 hasConceptScore W4379519265C2780451532 @default.
• W4379519265 hasConceptScore W4379519265C38652104 @default.
• W4379519265 hasConceptScore W4379519265C41008148 @default.
• W4379519265 hasConceptScore W4379519265C48145219 @default.
• W4379519265 hasLocation W43795192651 @default.
• W4379519265 hasLocation W43795192652 @default.
• W4379519265 hasLocation W43795192653 @default.
• W4379519265 hasOpenAccess W4379519265 @default.
• W4379519265 hasPrimaryLocation W43795192651 @default.
• W4379519265 hasRelatedWork W1980748319 @default.
• W4379519265 hasRelatedWork W2146948107 @default.
• W4379519265 hasRelatedWork W2963461172 @default.
• W4379519265 hasRelatedWork W3031263788 @default.
• W4379519265 hasRelatedWork W3101260801 @default.
• W4379519265 hasRelatedWork W3193140313 @default.
• W4379519265 hasRelatedWork W3214642209 @default.
• W4379519265 hasRelatedWork W4226048468 @default.
• W4379519265 hasRelatedWork W4308949089 @default.

• next