Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308648312> ?p ?o ?g. }
- W4308648312 abstract "Code generation aims to generate a code snippet automatically from natural language descriptions. Generally, the mainstream code generation methods rely on a large amount of paired training data, including both the natural language description and the code. However, in some domain-specific scenarios, building such a large paired corpus for code generation is difficult because there is no directly available pairing data, and a lot of effort is required to manually write the code descriptions to construct a high-quality training dataset. Due to the limited training data, the generation model cannot be well trained and is likely to be overfitting, making the model's performance unsatisfactory for real-world use. To this end, in this paper, we propose a task augmentation method that incorporates domain knowledge into code generation models through auxiliary tasks and a Subtoken-TranX model by extending the original TranX model to support subtoken-level code generation. To verify our proposed approach, we collect a real-world code generation dataset and conduct experiments on it. Our experimental results demonstrate that the subtoken-level TranX model outperforms the original TranX model and the Transformer model on our dataset, and the exact match accuracy of Subtoken-TranX improves significantly by 12.75% with the help of our task augmentation method. The model performance on several code categories has satisfied the requirements for application in industrial systems. Our proposed approach has been adopted by Alibaba's BizCook platform. To the best of our knowledge, this is the first domain code generation system adopted in industrial development environments." @default.
- W4308648312 created "2022-11-13" @default.
- W4308648312 creator A5009535551 @default.
- W4308648312 creator A5012564751 @default.
- W4308648312 creator A5045653035 @default.
- W4308648312 creator A5049423110 @default.
- W4308648312 creator A5077542599 @default.
- W4308648312 creator A5081083643 @default.
- W4308648312 date "2022-11-07" @default.
- W4308648312 modified "2023-09-27" @default.
- W4308648312 title "Incorporating domain knowledge through task augmentation for front-end JavaScript code generation" @default.
- W4308648312 cites W1902237438 @default.
- W4308648312 cites W2889467844 @default.
- W4308648312 cites W2890867094 @default.
- W4308648312 cites W2962728167 @default.
- W4308648312 cites W2962784628 @default.
- W4308648312 cites W2963357517 @default.
- W4308648312 cites W2963794306 @default.
- W4308648312 cites W2963829526 @default.
- W4308648312 cites W2963868406 @default.
- W4308648312 cites W2964325845 @default.
- W4308648312 cites W2997847174 @default.
- W4308648312 cites W3034976548 @default.
- W4308648312 cites W3105247453 @default.
- W4308648312 cites W3108032709 @default.
- W4308648312 cites W3149750418 @default.
- W4308648312 cites W3170092793 @default.
- W4308648312 cites W3172275282 @default.
- W4308648312 cites W3176868790 @default.
- W4308648312 cites W3198685994 @default.
- W4308648312 doi "https://doi.org/10.1145/3540250.3558965" @default.
- W4308648312 hasPublicationYear "2022" @default.
- W4308648312 type Work @default.
- W4308648312 citedByCount "2" @default.
- W4308648312 countsByYear W43086483122023 @default.
- W4308648312 crossrefType "proceedings-article" @default.
- W4308648312 hasAuthorship W4308648312A5009535551 @default.
- W4308648312 hasAuthorship W4308648312A5012564751 @default.
- W4308648312 hasAuthorship W4308648312A5045653035 @default.
- W4308648312 hasAuthorship W4308648312A5049423110 @default.
- W4308648312 hasAuthorship W4308648312A5077542599 @default.
- W4308648312 hasAuthorship W4308648312A5081083643 @default.
- W4308648312 hasBestOaLocation W43086483122 @default.
- W4308648312 hasConcept C111919701 @default.
- W4308648312 hasConcept C119857082 @default.
- W4308648312 hasConcept C133162039 @default.
- W4308648312 hasConcept C134306372 @default.
- W4308648312 hasConcept C137293760 @default.
- W4308648312 hasConcept C151578736 @default.
- W4308648312 hasConcept C154945302 @default.
- W4308648312 hasConcept C162324750 @default.
- W4308648312 hasConcept C177264268 @default.
- W4308648312 hasConcept C187736073 @default.
- W4308648312 hasConcept C199360897 @default.
- W4308648312 hasConcept C204321447 @default.
- W4308648312 hasConcept C22019652 @default.
- W4308648312 hasConcept C26517878 @default.
- W4308648312 hasConcept C2776760102 @default.
- W4308648312 hasConcept C2780451532 @default.
- W4308648312 hasConcept C33923547 @default.
- W4308648312 hasConcept C36503486 @default.
- W4308648312 hasConcept C41008148 @default.
- W4308648312 hasConcept C43126263 @default.
- W4308648312 hasConcept C50644808 @default.
- W4308648312 hasConcept C544833334 @default.
- W4308648312 hasConceptScore W4308648312C111919701 @default.
- W4308648312 hasConceptScore W4308648312C119857082 @default.
- W4308648312 hasConceptScore W4308648312C133162039 @default.
- W4308648312 hasConceptScore W4308648312C134306372 @default.
- W4308648312 hasConceptScore W4308648312C137293760 @default.
- W4308648312 hasConceptScore W4308648312C151578736 @default.
- W4308648312 hasConceptScore W4308648312C154945302 @default.
- W4308648312 hasConceptScore W4308648312C162324750 @default.
- W4308648312 hasConceptScore W4308648312C177264268 @default.
- W4308648312 hasConceptScore W4308648312C187736073 @default.
- W4308648312 hasConceptScore W4308648312C199360897 @default.
- W4308648312 hasConceptScore W4308648312C204321447 @default.
- W4308648312 hasConceptScore W4308648312C22019652 @default.
- W4308648312 hasConceptScore W4308648312C26517878 @default.
- W4308648312 hasConceptScore W4308648312C2776760102 @default.
- W4308648312 hasConceptScore W4308648312C2780451532 @default.
- W4308648312 hasConceptScore W4308648312C33923547 @default.
- W4308648312 hasConceptScore W4308648312C36503486 @default.
- W4308648312 hasConceptScore W4308648312C41008148 @default.
- W4308648312 hasConceptScore W4308648312C43126263 @default.
- W4308648312 hasConceptScore W4308648312C50644808 @default.
- W4308648312 hasConceptScore W4308648312C544833334 @default.
- W4308648312 hasLocation W43086483121 @default.
- W4308648312 hasLocation W43086483122 @default.
- W4308648312 hasOpenAccess W4308648312 @default.
- W4308648312 hasPrimaryLocation W43086483121 @default.
- W4308648312 hasRelatedWork W2086567499 @default.
- W4308648312 hasRelatedWork W2382513971 @default.
- W4308648312 hasRelatedWork W2384847609 @default.
- W4308648312 hasRelatedWork W2770458676 @default.
- W4308648312 hasRelatedWork W283806354 @default.
- W4308648312 hasRelatedWork W3025993830 @default.
- W4308648312 hasRelatedWork W3087261808 @default.
- W4308648312 hasRelatedWork W4287196823 @default.
- W4308648312 hasRelatedWork W4287665582 @default.