FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387359991> ?p ?o ?g. }

• W4387359991 abstract "Based on developer needs and usage scenarios, API (Application Programming Interface) recommendation is the process of assisting developers in finding the required API among numerous candidate APIs. Previous studies mainly modeled API recommendation as the recommendation task, which can recommend multiple candidate APIs for the given query, and developers may not yet be able to find what they need. Motivated by the neural machine translation research domain, we can model this problem as the generation task, which aims to directly generate the required API for the developer query. After our preliminary investigation, we find the performance of this intuitive approach is not promising. The reason is that there exists an error when generating the prefixes of the API. However, developers may know certain API prefix information during actual development in most cases. Therefore, we model this problem as the automatic completion task and propose a novel approach APICom based on prompt learning, which can generate API related to the query according to the prompts (i.e., API prefix information). Moreover, the effectiveness of APICom highly depends on the quality of the training dataset. In this study, we further design a novel gradient-based adversarial training method ATCom for data augmentation, which can improve the normalized stability when generating adversarial examples. To evaluate the effectiveness of APICom, we consider a corpus of 33k developer queries and corresponding APIs. Compared with the state-of-the-art baselines, our experimental results show that APICom can outperform all baselines by at least 40.02%, 13.20%, and 16.31% in terms of the performance measures EM@1, MRR, and MAP. Finally, our ablation studies confirm the effectiveness of our component setting (such as our designed adversarial training method, our used pre-trained model, and prompt learning) in APICom." @default.
• W4387359991 created "2023-10-06" @default.
• W4387359991 creator A5015398815 @default.
• W4387359991 creator A5017683801 @default.
• W4387359991 creator A5034858258 @default.
• W4387359991 creator A5066226804 @default.
• W4387359991 creator A5066596896 @default.
• W4387359991 creator A5081742959 @default.
• W4387359991 date "2023-08-04" @default.
• W4387359991 modified "2023-10-06" @default.
• W4387359991 title "APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation" @default.
• W4387359991 cites W2194775991 @default.
• W4387359991 cites W2267186426 @default.
• W4387359991 cites W2344367508 @default.
• W4387359991 cites W2402619042 @default.
• W4387359991 cites W2406365535 @default.
• W4387359991 cites W2888017562 @default.
• W4387359991 cites W2971296908 @default.
• W4387359991 cites W3035204084 @default.
• W4387359991 cites W3105604018 @default.
• W4387359991 cites W3170092793 @default.
• W4387359991 cites W3179515446 @default.
• W4387359991 cites W3198685994 @default.
• W4387359991 cites W4200276311 @default.
• W4387359991 cites W4296143043 @default.
• W4387359991 cites W4311423650 @default.
• W4387359991 doi "https://doi.org/10.1145/3609437.3609450" @default.
• W4387359991 hasPublicationYear "2023" @default.
• W4387359991 type Work @default.
• W4387359991 citedByCount "0" @default.
• W4387359991 crossrefType "proceedings-article" @default.
• W4387359991 hasAuthorship W4387359991A5015398815 @default.
• W4387359991 hasAuthorship W4387359991A5017683801 @default.
• W4387359991 hasAuthorship W4387359991A5034858258 @default.
• W4387359991 hasAuthorship W4387359991A5066226804 @default.
• W4387359991 hasAuthorship W4387359991A5066596896 @default.
• W4387359991 hasAuthorship W4387359991A5081742959 @default.
• W4387359991 hasConcept C119857082 @default.
• W4387359991 hasConcept C124101348 @default.
• W4387359991 hasConcept C134306372 @default.
• W4387359991 hasConcept C154945302 @default.
• W4387359991 hasConcept C162324750 @default.
• W4387359991 hasConcept C187736073 @default.
• W4387359991 hasConcept C199360897 @default.
• W4387359991 hasConcept C23123220 @default.
• W4387359991 hasConcept C2780451532 @default.
• W4387359991 hasConcept C33923547 @default.
• W4387359991 hasConcept C36503486 @default.
• W4387359991 hasConcept C41008148 @default.
• W4387359991 hasConcept C98045186 @default.
• W4387359991 hasConcept C99613125 @default.
• W4387359991 hasConceptScore W4387359991C119857082 @default.
• W4387359991 hasConceptScore W4387359991C124101348 @default.
• W4387359991 hasConceptScore W4387359991C134306372 @default.
• W4387359991 hasConceptScore W4387359991C154945302 @default.
• W4387359991 hasConceptScore W4387359991C162324750 @default.
• W4387359991 hasConceptScore W4387359991C187736073 @default.
• W4387359991 hasConceptScore W4387359991C199360897 @default.
• W4387359991 hasConceptScore W4387359991C23123220 @default.
• W4387359991 hasConceptScore W4387359991C2780451532 @default.
• W4387359991 hasConceptScore W4387359991C33923547 @default.
• W4387359991 hasConceptScore W4387359991C36503486 @default.
• W4387359991 hasConceptScore W4387359991C41008148 @default.
• W4387359991 hasConceptScore W4387359991C98045186 @default.
• W4387359991 hasConceptScore W4387359991C99613125 @default.
• W4387359991 hasLocation W43873599911 @default.
• W4387359991 hasOpenAccess W4387359991 @default.
• W4387359991 hasPrimaryLocation W43873599911 @default.
• W4387359991 hasRelatedWork W2331739042 @default.
• W4387359991 hasRelatedWork W2373456246 @default.
• W4387359991 hasRelatedWork W2413419736 @default.
• W4387359991 hasRelatedWork W2548721895 @default.
• W4387359991 hasRelatedWork W2961085424 @default.
• W4387359991 hasRelatedWork W4205958290 @default.
• W4387359991 hasRelatedWork W4286629047 @default.
• W4387359991 hasRelatedWork W4306674287 @default.
• W4387359991 hasRelatedWork W4384212932 @default.
• W4387359991 hasRelatedWork W4224009465 @default.
• W4387359991 isParatext "false" @default.
• W4387359991 isRetracted "false" @default.
• W4387359991 workType "article" @default.