Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287765975> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4287765975 abstract "Named entity recognition (NER) is frequently addressed as a sequence classification task where each input consists of one sentence of text. It is nevertheless clear that useful information for the task can often be found outside of the scope of a single-sentence context. Recently proposed self-attention models such as BERT can both efficiently capture long-distance relationships in input as well as represent inputs consisting of several sentences, creating new opportunitites for approaches that incorporate cross-sentence information in natural language processing tasks. In this paper, we present a systematic study exploring the use of cross-sentence information for NER using BERT models in five languages. We find that adding context in the form of additional sentences to BERT input systematically increases NER performance on all of the tested languages and models. Including multiple sentences in each input also allows us to study the predictions of the same sentences in different contexts. We propose a straightforward method, Contextual Majority Voting (CMV), to combine different predictions for sentences and demonstrate this to further increase NER performance with BERT. Our approach does not require any changes to the underlying BERT architecture, rather relying on restructuring examples for training and prediction. Evaluation on established datasets, including the CoNLL'02 and CoNLL'03 NER benchmarks, demonstrates that our proposed approach can improve on the state-of-the-art NER results on English, Dutch, and Finnish, achieves the best reported BERT-based results on German, and is on par with performance reported with other BERT-based approaches in Spanish. We release all methods implemented in this work under open licenses." @default.
- W4287765975 created "2022-07-26" @default.
- W4287765975 creator A5018656314 @default.
- W4287765975 creator A5066925770 @default.
- W4287765975 date "2020-06-02" @default.
- W4287765975 modified "2023-10-16" @default.
- W4287765975 title "Exploring Cross-sentence Contexts for Named Entity Recognition with BERT" @default.
- W4287765975 doi "https://doi.org/10.48550/arxiv.2006.01563" @default.
- W4287765975 hasPublicationYear "2020" @default.
- W4287765975 type Work @default.
- W4287765975 citedByCount "0" @default.
- W4287765975 crossrefType "posted-content" @default.
- W4287765975 hasAuthorship W4287765975A5018656314 @default.
- W4287765975 hasAuthorship W4287765975A5066925770 @default.
- W4287765975 hasBestOaLocation W42877659751 @default.
- W4287765975 hasConcept C137293760 @default.
- W4287765975 hasConcept C138885662 @default.
- W4287765975 hasConcept C151730666 @default.
- W4287765975 hasConcept C154775046 @default.
- W4287765975 hasConcept C154945302 @default.
- W4287765975 hasConcept C162324750 @default.
- W4287765975 hasConcept C187736073 @default.
- W4287765975 hasConcept C199360897 @default.
- W4287765975 hasConcept C204321447 @default.
- W4287765975 hasConcept C2777530160 @default.
- W4287765975 hasConcept C2778012447 @default.
- W4287765975 hasConcept C2779135771 @default.
- W4287765975 hasConcept C2779343474 @default.
- W4287765975 hasConcept C2780451532 @default.
- W4287765975 hasConcept C41008148 @default.
- W4287765975 hasConcept C41895202 @default.
- W4287765975 hasConcept C4554734 @default.
- W4287765975 hasConcept C86803240 @default.
- W4287765975 hasConcept C96711827 @default.
- W4287765975 hasConceptScore W4287765975C137293760 @default.
- W4287765975 hasConceptScore W4287765975C138885662 @default.
- W4287765975 hasConceptScore W4287765975C151730666 @default.
- W4287765975 hasConceptScore W4287765975C154775046 @default.
- W4287765975 hasConceptScore W4287765975C154945302 @default.
- W4287765975 hasConceptScore W4287765975C162324750 @default.
- W4287765975 hasConceptScore W4287765975C187736073 @default.
- W4287765975 hasConceptScore W4287765975C199360897 @default.
- W4287765975 hasConceptScore W4287765975C204321447 @default.
- W4287765975 hasConceptScore W4287765975C2777530160 @default.
- W4287765975 hasConceptScore W4287765975C2778012447 @default.
- W4287765975 hasConceptScore W4287765975C2779135771 @default.
- W4287765975 hasConceptScore W4287765975C2779343474 @default.
- W4287765975 hasConceptScore W4287765975C2780451532 @default.
- W4287765975 hasConceptScore W4287765975C41008148 @default.
- W4287765975 hasConceptScore W4287765975C41895202 @default.
- W4287765975 hasConceptScore W4287765975C4554734 @default.
- W4287765975 hasConceptScore W4287765975C86803240 @default.
- W4287765975 hasConceptScore W4287765975C96711827 @default.
- W4287765975 hasLocation W42877659751 @default.
- W4287765975 hasOpenAccess W4287765975 @default.
- W4287765975 hasPrimaryLocation W42877659751 @default.
- W4287765975 hasRelatedWork W11196620 @default.
- W4287765975 hasRelatedWork W11298561 @default.
- W4287765975 hasRelatedWork W13618705 @default.
- W4287765975 hasRelatedWork W2305510 @default.
- W4287765975 hasRelatedWork W3983095 @default.
- W4287765975 hasRelatedWork W5053386 @default.
- W4287765975 hasRelatedWork W6169193 @default.
- W4287765975 hasRelatedWork W8902685 @default.
- W4287765975 hasRelatedWork W975493 @default.
- W4287765975 hasRelatedWork W8411197 @default.
- W4287765975 isParatext "false" @default.
- W4287765975 isRetracted "false" @default.
- W4287765975 workType "article" @default.