Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382519199> ?p ?o ?g. }
- W4382519199 endingPage "365" @default.
- W4382519199 startingPage "349" @default.
- W4382519199 abstract "We propose in this work a new approach that aims to transform a classification corpus into an STS (Semantic Textual Similarity) one. In that sense, we use BERT (Bidirectional Encoder Representations from Transformers) to validate our hypothesis, i.e., a multi-level classification dataset can be converted into an STS dataset which improves the fine-tuning step and evidences the proposed corpus. Also, in our approach, we trained from scratching a BERT model considering the legal texts, called JurisBert which reveals a considered improvement in fastness and precision, and it requires less computational resources than other approaches. JurisBERT uses the concept of sub-language, i.e., a model pre-trained in a language (Brazilian Portuguese) passes through refining (fine-tuning) to better attend to a specific domain, in our case, the legal field. JurisBERT uses 24k pairs of ementas with degrees of similarity varying from 0 to 3. We got this data from search mechanisms available on the court websites to validate the model with real-world data. Our experiments showed JurisBERT is better than other models such as multilingual BERT and BERTimbau with $$3.30%$$ better precision ( $$F_1$$ ), 5 times reduced training time, and using accessible hardware, i.e., low-cost GPGPU architecture. The source code is available at https://github.com/alfaneo-ai/brazilian-legal-text-dataset and the model is here: https://huggingface.co/alfaneo ." @default.
- W4382519199 created "2023-06-30" @default.
- W4382519199 creator A5047727871 @default.
- W4382519199 creator A5061372687 @default.
- W4382519199 creator A5067397008 @default.
- W4382519199 date "2023-01-01" @default.
- W4382519199 modified "2023-09-27" @default.
- W4382519199 title "JurisBERT: A New Approach that Converts a Classification Corpus into an STS One" @default.
- W4382519199 cites W2024948483 @default.
- W4382519199 cites W2250539671 @default.
- W4382519199 cites W2888643140 @default.
- W4382519199 cites W2891177506 @default.
- W4382519199 cites W2899663614 @default.
- W4382519199 cites W2964121744 @default.
- W4382519199 cites W2965373594 @default.
- W4382519199 cites W2970771982 @default.
- W4382519199 cites W3008931407 @default.
- W4382519199 cites W3030156796 @default.
- W4382519199 cites W3096266342 @default.
- W4382519199 cites W3123742788 @default.
- W4382519199 cites W3178036561 @default.
- W4382519199 cites W3214032513 @default.
- W4382519199 cites W4221159403 @default.
- W4382519199 cites W4282586470 @default.
- W4382519199 cites W4288253152 @default.
- W4382519199 cites W4299585995 @default.
- W4382519199 cites W4302400662 @default.
- W4382519199 doi "https://doi.org/10.1007/978-3-031-36805-9_24" @default.
- W4382519199 hasPublicationYear "2023" @default.
- W4382519199 type Work @default.
- W4382519199 citedByCount "0" @default.
- W4382519199 crossrefType "book-chapter" @default.
- W4382519199 hasAuthorship W4382519199A5047727871 @default.
- W4382519199 hasAuthorship W4382519199A5061372687 @default.
- W4382519199 hasAuthorship W4382519199A5067397008 @default.
- W4382519199 hasConcept C103278499 @default.
- W4382519199 hasConcept C111919701 @default.
- W4382519199 hasConcept C115961682 @default.
- W4382519199 hasConcept C118505674 @default.
- W4382519199 hasConcept C119857082 @default.
- W4382519199 hasConcept C121332964 @default.
- W4382519199 hasConcept C130318100 @default.
- W4382519199 hasConcept C134306372 @default.
- W4382519199 hasConcept C137293760 @default.
- W4382519199 hasConcept C154945302 @default.
- W4382519199 hasConcept C165801399 @default.
- W4382519199 hasConcept C177264268 @default.
- W4382519199 hasConcept C199360897 @default.
- W4382519199 hasConcept C202444582 @default.
- W4382519199 hasConcept C204321447 @default.
- W4382519199 hasConcept C23123220 @default.
- W4382519199 hasConcept C2776760102 @default.
- W4382519199 hasConcept C33923547 @default.
- W4382519199 hasConcept C36503486 @default.
- W4382519199 hasConcept C41008148 @default.
- W4382519199 hasConcept C43126263 @default.
- W4382519199 hasConcept C62520636 @default.
- W4382519199 hasConcept C66322947 @default.
- W4382519199 hasConcept C9652623 @default.
- W4382519199 hasConceptScore W4382519199C103278499 @default.
- W4382519199 hasConceptScore W4382519199C111919701 @default.
- W4382519199 hasConceptScore W4382519199C115961682 @default.
- W4382519199 hasConceptScore W4382519199C118505674 @default.
- W4382519199 hasConceptScore W4382519199C119857082 @default.
- W4382519199 hasConceptScore W4382519199C121332964 @default.
- W4382519199 hasConceptScore W4382519199C130318100 @default.
- W4382519199 hasConceptScore W4382519199C134306372 @default.
- W4382519199 hasConceptScore W4382519199C137293760 @default.
- W4382519199 hasConceptScore W4382519199C154945302 @default.
- W4382519199 hasConceptScore W4382519199C165801399 @default.
- W4382519199 hasConceptScore W4382519199C177264268 @default.
- W4382519199 hasConceptScore W4382519199C199360897 @default.
- W4382519199 hasConceptScore W4382519199C202444582 @default.
- W4382519199 hasConceptScore W4382519199C204321447 @default.
- W4382519199 hasConceptScore W4382519199C23123220 @default.
- W4382519199 hasConceptScore W4382519199C2776760102 @default.
- W4382519199 hasConceptScore W4382519199C33923547 @default.
- W4382519199 hasConceptScore W4382519199C36503486 @default.
- W4382519199 hasConceptScore W4382519199C41008148 @default.
- W4382519199 hasConceptScore W4382519199C43126263 @default.
- W4382519199 hasConceptScore W4382519199C62520636 @default.
- W4382519199 hasConceptScore W4382519199C66322947 @default.
- W4382519199 hasConceptScore W4382519199C9652623 @default.
- W4382519199 hasLocation W43825191991 @default.
- W4382519199 hasOpenAccess W4382519199 @default.
- W4382519199 hasPrimaryLocation W43825191991 @default.
- W4382519199 hasRelatedWork W2186284405 @default.
- W4382519199 hasRelatedWork W3023944410 @default.
- W4382519199 hasRelatedWork W3042381743 @default.
- W4382519199 hasRelatedWork W3100140062 @default.
- W4382519199 hasRelatedWork W3177381119 @default.
- W4382519199 hasRelatedWork W3207932232 @default.
- W4382519199 hasRelatedWork W3216821104 @default.
- W4382519199 hasRelatedWork W4232527877 @default.
- W4382519199 hasRelatedWork W4281690070 @default.
- W4382519199 hasRelatedWork W4287890973 @default.
- W4382519199 isParatext "false" @default.
- W4382519199 isRetracted "false" @default.