Matches in SemOpenAlex for { <https://semopenalex.org/work/W3189653670> ?p ?o ?g. }
- W3189653670 abstract "Code completion aims at speeding up code writing by predicting the next code token(s) the developer is likely to write. Works in this field focused on improving the accuracy of the generated predictions, with substantial leaps forward made possible by deep learning (DL) models. However, code completion techniques are mostly evaluated in the scenario of predicting the next token to type, with few exceptions pushing the boundaries to the prediction of an entire code statement. Thus, little is known about the performance of state-of-the-art code completion approaches in more challenging scenarios in which, for example, an entire code block must be generated. We present a large-scale study exploring the capabilities of state-of-the-art Transformer-based models in supporting code completion at different granularity levels, including single tokens, one or multiple entire statements, up to entire code blocks (e.g., the iterated block of a for loop). We experimented with several variants of two recently proposed Transformer-based models, namely RoBERTa and the Text-To-Text Transfer Transformer (T5), for the task of code completion. The achieved results show that Transformer-based models, and in particular the T5, represent a viable solution for code completion, with perfect predictions ranging from ~29%, obtained when asking the model to guess entire blocks, up to ~69%, reached in the simpler scenario of few tokens masked from the same code statement." @default.
- W3189653670 created "2021-08-16" @default.
- W3189653670 creator A5025099559 @default.
- W3189653670 creator A5027300975 @default.
- W3189653670 creator A5030004305 @default.
- W3189653670 creator A5041262116 @default.
- W3189653670 creator A5042595047 @default.
- W3189653670 creator A5056526226 @default.
- W3189653670 creator A5060494552 @default.
- W3189653670 creator A5069505458 @default.
- W3189653670 date "2021-08-03" @default.
- W3189653670 modified "2023-09-27" @default.
- W3189653670 title "An Empirical Study on the Usage of Transformer Models for Code Completion" @default.
- W3189653670 cites W1585991568 @default.
- W3189653670 cites W1647671624 @default.
- W3189653670 cites W1970018430 @default.
- W3189653670 cites W1970607969 @default.
- W3189653670 cites W1974020522 @default.
- W3189653670 cites W1977971855 @default.
- W3189653670 cites W1980450075 @default.
- W3189653670 cites W1985514943 @default.
- W3189653670 cites W2018389835 @default.
- W3189653670 cites W2052456234 @default.
- W3189653670 cites W2059556545 @default.
- W3189653670 cites W2080579313 @default.
- W3189653670 cites W2083878868 @default.
- W3189653670 cites W2084413241 @default.
- W3189653670 cites W2096061896 @default.
- W3189653670 cites W2106259924 @default.
- W3189653670 cites W2110065044 @default.
- W3189653670 cites W2115259925 @default.
- W3189653670 cites W2122076271 @default.
- W3189653670 cites W2134092629 @default.
- W3189653670 cites W2138318139 @default.
- W3189653670 cites W2142403498 @default.
- W3189653670 cites W2143861926 @default.
- W3189653670 cites W2153943889 @default.
- W3189653670 cites W2157976942 @default.
- W3189653670 cites W2165747537 @default.
- W3189653670 cites W2170460608 @default.
- W3189653670 cites W2266912522 @default.
- W3189653670 cites W2400997415 @default.
- W3189653670 cites W2402619042 @default.
- W3189653670 cites W2478709442 @default.
- W3189653670 cites W2557805692 @default.
- W3189653670 cites W2740130862 @default.
- W3189653670 cites W2768007977 @default.
- W3189653670 cites W2797862469 @default.
- W3189653670 cites W2883889688 @default.
- W3189653670 cites W2884670025 @default.
- W3189653670 cites W2907705732 @default.
- W3189653670 cites W2921792613 @default.
- W3189653670 cites W2953495996 @default.
- W3189653670 cites W2954451301 @default.
- W3189653670 cites W2954823997 @default.
- W3189653670 cites W2963250244 @default.
- W3189653670 cites W2963341956 @default.
- W3189653670 cites W2963403868 @default.
- W3189653670 cites W2964150020 @default.
- W3189653670 cites W2964322208 @default.
- W3189653670 cites W2965373594 @default.
- W3189653670 cites W2972082064 @default.
- W3189653670 cites W2973529529 @default.
- W3189653670 cites W2979679630 @default.
- W3189653670 cites W2980282514 @default.
- W3189653670 cites W2981852735 @default.
- W3189653670 cites W2999760805 @default.
- W3189653670 cites W3015810308 @default.
- W3189653670 cites W3021206621 @default.
- W3189653670 cites W3028741749 @default.
- W3189653670 cites W3034549508 @default.
- W3189653670 cites W3035300716 @default.
- W3189653670 cites W3081454995 @default.
- W3189653670 cites W3085219557 @default.
- W3189653670 cites W3089307846 @default.
- W3189653670 cites W3099302725 @default.
- W3189653670 cites W3105398568 @default.
- W3189653670 cites W3105903381 @default.
- W3189653670 cites W3108032709 @default.
- W3189653670 cites W3161677724 @default.
- W3189653670 cites W3161997752 @default.
- W3189653670 cites W3162689995 @default.
- W3189653670 cites W3173543662 @default.
- W3189653670 cites W3176740355 @default.
- W3189653670 cites W3195421019 @default.
- W3189653670 cites W46679369 @default.
- W3189653670 cites W1857789879 @default.
- W3189653670 hasPublicationYear "2021" @default.
- W3189653670 type Work @default.
- W3189653670 sameAs 3189653670 @default.
- W3189653670 citedByCount "1" @default.
- W3189653670 countsByYear W31896536702021 @default.
- W3189653670 crossrefType "posted-content" @default.
- W3189653670 hasAuthorship W3189653670A5025099559 @default.
- W3189653670 hasAuthorship W3189653670A5027300975 @default.
- W3189653670 hasAuthorship W3189653670A5030004305 @default.
- W3189653670 hasAuthorship W3189653670A5041262116 @default.
- W3189653670 hasAuthorship W3189653670A5042595047 @default.
- W3189653670 hasAuthorship W3189653670A5056526226 @default.
- W3189653670 hasAuthorship W3189653670A5060494552 @default.