Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313648295> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4313648295 abstract "Abstract The analysis of software requirement specifications (SRS) using Natural Language Processing (NLP) methods has been an important study area in the software engineering field in recent years. Especially thanks to the advances brought by deep learning and transfer learning approaches in NLP, SRS data can be utilized for various learning tasks more easily. In this study, we employ a three-stage domain-adaptive fine-tuning approach for three prediction tasks regarding software requirements, which improve the model robustness on a real distribution shift. The multi-class classification tasks involve predicting the type, priority and severity of the requirement texts specified by the users. We compare our results with strong classification baselines such as word embedding pooling and Sentence BERT, and show that the adaptive fine-tuning leads to performance improvements across the tasks. We find that an adaptively fine-tuned model can be specialized to particular data distribution, which is able to generate accurate results and learns from abundantly available textual data in software engineering task management systems." @default.
- W4313648295 created "2023-01-07" @default.
- W4313648295 creator A5003732278 @default.
- W4313648295 creator A5011860360 @default.
- W4313648295 creator A5015457657 @default.
- W4313648295 creator A5070091996 @default.
- W4313648295 date "2023-01-06" @default.
- W4313648295 modified "2023-09-25" @default.
- W4313648295 title "Adaptive Fine-tuning for Multiclass Classification over Software Requirement Data" @default.
- W4313648295 doi "https://doi.org/10.21203/rs.3.rs-2434133/v1" @default.
- W4313648295 hasPublicationYear "2023" @default.
- W4313648295 type Work @default.
- W4313648295 citedByCount "0" @default.
- W4313648295 crossrefType "posted-content" @default.
- W4313648295 hasAuthorship W4313648295A5003732278 @default.
- W4313648295 hasAuthorship W4313648295A5011860360 @default.
- W4313648295 hasAuthorship W4313648295A5015457657 @default.
- W4313648295 hasAuthorship W4313648295A5070091996 @default.
- W4313648295 hasBestOaLocation W43136482951 @default.
- W4313648295 hasConcept C104317684 @default.
- W4313648295 hasConcept C108583219 @default.
- W4313648295 hasConcept C119857082 @default.
- W4313648295 hasConcept C150899416 @default.
- W4313648295 hasConcept C154945302 @default.
- W4313648295 hasConcept C162324750 @default.
- W4313648295 hasConcept C185592680 @default.
- W4313648295 hasConcept C187736073 @default.
- W4313648295 hasConcept C199360897 @default.
- W4313648295 hasConcept C202444582 @default.
- W4313648295 hasConcept C204321447 @default.
- W4313648295 hasConcept C2777530160 @default.
- W4313648295 hasConcept C2777904410 @default.
- W4313648295 hasConcept C2780451532 @default.
- W4313648295 hasConcept C33923547 @default.
- W4313648295 hasConcept C41008148 @default.
- W4313648295 hasConcept C41608201 @default.
- W4313648295 hasConcept C55493867 @default.
- W4313648295 hasConcept C63479239 @default.
- W4313648295 hasConcept C70437156 @default.
- W4313648295 hasConcept C9652623 @default.
- W4313648295 hasConceptScore W4313648295C104317684 @default.
- W4313648295 hasConceptScore W4313648295C108583219 @default.
- W4313648295 hasConceptScore W4313648295C119857082 @default.
- W4313648295 hasConceptScore W4313648295C150899416 @default.
- W4313648295 hasConceptScore W4313648295C154945302 @default.
- W4313648295 hasConceptScore W4313648295C162324750 @default.
- W4313648295 hasConceptScore W4313648295C185592680 @default.
- W4313648295 hasConceptScore W4313648295C187736073 @default.
- W4313648295 hasConceptScore W4313648295C199360897 @default.
- W4313648295 hasConceptScore W4313648295C202444582 @default.
- W4313648295 hasConceptScore W4313648295C204321447 @default.
- W4313648295 hasConceptScore W4313648295C2777530160 @default.
- W4313648295 hasConceptScore W4313648295C2777904410 @default.
- W4313648295 hasConceptScore W4313648295C2780451532 @default.
- W4313648295 hasConceptScore W4313648295C33923547 @default.
- W4313648295 hasConceptScore W4313648295C41008148 @default.
- W4313648295 hasConceptScore W4313648295C41608201 @default.
- W4313648295 hasConceptScore W4313648295C55493867 @default.
- W4313648295 hasConceptScore W4313648295C63479239 @default.
- W4313648295 hasConceptScore W4313648295C70437156 @default.
- W4313648295 hasConceptScore W4313648295C9652623 @default.
- W4313648295 hasLocation W43136482951 @default.
- W4313648295 hasLocation W43136482952 @default.
- W4313648295 hasOpenAccess W4313648295 @default.
- W4313648295 hasPrimaryLocation W43136482951 @default.
- W4313648295 hasRelatedWork W2946016983 @default.
- W4313648295 hasRelatedWork W2960456850 @default.
- W4313648295 hasRelatedWork W4296990061 @default.
- W4313648295 hasRelatedWork W4312200629 @default.
- W4313648295 hasRelatedWork W4312831135 @default.
- W4313648295 hasRelatedWork W4317565044 @default.
- W4313648295 hasRelatedWork W4318834068 @default.
- W4313648295 hasRelatedWork W4318957922 @default.
- W4313648295 hasRelatedWork W4380611590 @default.
- W4313648295 hasRelatedWork W4382286161 @default.
- W4313648295 isParatext "false" @default.
- W4313648295 isRetracted "false" @default.
- W4313648295 workType "article" @default.