Matches in SemOpenAlex for { <https://semopenalex.org/work/W3195655884> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3195655884 abstract "In this digital era, the textual content has become a seemingly ubiquitous part of our life. Natural Language Processing (NLP) empowers machines to comprehend the intricacies of textual data and eases human-computer interaction. Advancement in language modeling, continual learning, availability of a large amount of linguistic data, and large-scale computational power have made it feasible to train models for downstream tasks related to text analysis, including safety-critical ones, e.g., medical, airlines, etc. Compared to other deep learning (DL) models, NLP-based models are widely reused for various tasks. However, the reuse of pre-trained models in a new setting is still a complex task due to the limitations of the training dataset, model structure, specification, usage, etc. With this motivation, we study BERT, a vastly used language model (LM), from the direction of reusing in the code. We mined 80 posts from Stack Overflow related to BERT and found 4 types of bugs observed in clients’ code. Our results show that 13.75% are fairness, 28.75% are parameter, 15% are token, and 16.25% are version-related bugs." @default.
- W3195655884 created "2021-08-30" @default.
- W3195655884 creator A5020161255 @default.
- W3195655884 date "2021-08-18" @default.
- W3195655884 modified "2023-10-16" @default.
- W3195655884 title "Does reusing pre-trained NLP model propagate bugs?" @default.
- W3195655884 cites W2008085811 @default.
- W3195655884 cites W2010208284 @default.
- W3195655884 cites W2013638584 @default.
- W3195655884 cites W2018890516 @default.
- W3195655884 cites W2089759055 @default.
- W3195655884 cites W2101832700 @default.
- W3195655884 cites W2114056383 @default.
- W3195655884 cites W2114334695 @default.
- W3195655884 cites W2135541598 @default.
- W3195655884 cites W2138756793 @default.
- W3195655884 cites W2156778594 @default.
- W3195655884 cites W2618843390 @default.
- W3195655884 cites W2791170418 @default.
- W3195655884 cites W2850992922 @default.
- W3195655884 cites W2962741379 @default.
- W3195655884 cites W2963809228 @default.
- W3195655884 cites W2968594320 @default.
- W3195655884 cites W3035229828 @default.
- W3195655884 cites W3091633490 @default.
- W3195655884 cites W3093218477 @default.
- W3195655884 cites W3104103145 @default.
- W3195655884 cites W3105111366 @default.
- W3195655884 cites W3105259960 @default.
- W3195655884 cites W3133702157 @default.
- W3195655884 cites W4233434287 @default.
- W3195655884 doi "https://doi.org/10.1145/3468264.3473494" @default.
- W3195655884 hasPublicationYear "2021" @default.
- W3195655884 type Work @default.
- W3195655884 sameAs 3195655884 @default.
- W3195655884 citedByCount "0" @default.
- W3195655884 crossrefType "proceedings-article" @default.
- W3195655884 hasAuthorship W3195655884A5020161255 @default.
- W3195655884 hasBestOaLocation W31956558841 @default.
- W3195655884 hasConcept C119857082 @default.
- W3195655884 hasConcept C137293760 @default.
- W3195655884 hasConcept C154945302 @default.
- W3195655884 hasConcept C162324750 @default.
- W3195655884 hasConcept C177264268 @default.
- W3195655884 hasConcept C187736073 @default.
- W3195655884 hasConcept C18903297 @default.
- W3195655884 hasConcept C199360897 @default.
- W3195655884 hasConcept C204321447 @default.
- W3195655884 hasConcept C206588197 @default.
- W3195655884 hasConcept C2776760102 @default.
- W3195655884 hasConcept C2780451532 @default.
- W3195655884 hasConcept C38652104 @default.
- W3195655884 hasConcept C41008148 @default.
- W3195655884 hasConcept C48145219 @default.
- W3195655884 hasConcept C86803240 @default.
- W3195655884 hasConceptScore W3195655884C119857082 @default.
- W3195655884 hasConceptScore W3195655884C137293760 @default.
- W3195655884 hasConceptScore W3195655884C154945302 @default.
- W3195655884 hasConceptScore W3195655884C162324750 @default.
- W3195655884 hasConceptScore W3195655884C177264268 @default.
- W3195655884 hasConceptScore W3195655884C187736073 @default.
- W3195655884 hasConceptScore W3195655884C18903297 @default.
- W3195655884 hasConceptScore W3195655884C199360897 @default.
- W3195655884 hasConceptScore W3195655884C204321447 @default.
- W3195655884 hasConceptScore W3195655884C206588197 @default.
- W3195655884 hasConceptScore W3195655884C2776760102 @default.
- W3195655884 hasConceptScore W3195655884C2780451532 @default.
- W3195655884 hasConceptScore W3195655884C38652104 @default.
- W3195655884 hasConceptScore W3195655884C41008148 @default.
- W3195655884 hasConceptScore W3195655884C48145219 @default.
- W3195655884 hasConceptScore W3195655884C86803240 @default.
- W3195655884 hasLocation W31956558841 @default.
- W3195655884 hasOpenAccess W3195655884 @default.
- W3195655884 hasPrimaryLocation W31956558841 @default.
- W3195655884 hasRelatedWork W142374489 @default.
- W3195655884 hasRelatedWork W2081647779 @default.
- W3195655884 hasRelatedWork W2359001871 @default.
- W3195655884 hasRelatedWork W2384847609 @default.
- W3195655884 hasRelatedWork W2883550961 @default.
- W3195655884 hasRelatedWork W3107474891 @default.
- W3195655884 hasRelatedWork W3115399078 @default.
- W3195655884 hasRelatedWork W3185852197 @default.
- W3195655884 hasRelatedWork W4205820553 @default.
- W3195655884 hasRelatedWork W4294862481 @default.
- W3195655884 isParatext "false" @default.
- W3195655884 isRetracted "false" @default.
- W3195655884 magId "3195655884" @default.
- W3195655884 workType "article" @default.