Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122473522> ?p ?o ?g. }
- W3122473522 abstract "A large body of the literature of automated program repair develops approaches where patches are generated to be validated against an oracle (e.g., a test suite). Because such an oracle can be imperfect, the generated patches, although validated by the oracle, may actually be incorrect. While the state of the art explore research directions that require dynamic information or that rely on manually-crafted heuristics, we study the benefit of learning code representations in order to learn deep features that may encode the properties of patch correctness. Our empirical work mainly investigates different representation learning approaches for code changes to derive embeddings that are amenable to similarity computations. We report on findings based on embeddings produced by pre-trained and re-trained neural networks. Experimental results demonstrate the potential of embeddings to empower learning algorithms in reasoning about patch correctness: a machine learning predictor with BERT transformer-based embeddings associated with logistic regression yielded an AUC value of about 0.8 in the prediction of patch correctness on a deduplicated dataset of 1000 labeled patches. Our investigations show that learned representations can lead to reasonable performance when comparing against the state-of-the-art, PATCH-SIM, which relies on dynamic information. These representations may further be complementary to features that were carefully (manually) engineered in the literature." @default.
- W3122473522 created "2021-02-01" @default.
- W3122473522 creator A5027475930 @default.
- W3122473522 creator A5035099591 @default.
- W3122473522 creator A5040326968 @default.
- W3122473522 creator A5050968170 @default.
- W3122473522 creator A5052007870 @default.
- W3122473522 creator A5070518954 @default.
- W3122473522 creator A5082835974 @default.
- W3122473522 date "2020-12-21" @default.
- W3122473522 modified "2023-10-16" @default.
- W3122473522 title "Evaluating representation learning of code changes for predicting patch correctness in program repair" @default.
- W3122473522 cites W1972978214 @default.
- W3122473522 cites W1977696633 @default.
- W3122473522 cites W2025791343 @default.
- W3122473522 cites W2061575154 @default.
- W3122473522 cites W2063387237 @default.
- W3122473522 cites W2122947685 @default.
- W3122473522 cites W2140609933 @default.
- W3122473522 cites W2145373440 @default.
- W3122473522 cites W2153881107 @default.
- W3122473522 cites W2156723666 @default.
- W3122473522 cites W2274071363 @default.
- W3122473522 cites W2360967250 @default.
- W3122473522 cites W2518136680 @default.
- W3122473522 cites W2735571786 @default.
- W3122473522 cites W2741328617 @default.
- W3122473522 cites W2741705590 @default.
- W3122473522 cites W2762550985 @default.
- W3122473522 cites W2791415964 @default.
- W3122473522 cites W2795030435 @default.
- W3122473522 cites W2795607463 @default.
- W3122473522 cites W2797053859 @default.
- W3122473522 cites W2804618777 @default.
- W3122473522 cites W2867448323 @default.
- W3122473522 cites W2883977877 @default.
- W3122473522 cites W2890606267 @default.
- W3122473522 cites W2904214673 @default.
- W3122473522 cites W2905489084 @default.
- W3122473522 cites W2908354350 @default.
- W3122473522 cites W2943748428 @default.
- W3122473522 cites W2954778170 @default.
- W3122473522 cites W2963341956 @default.
- W3122473522 cites W2963935794 @default.
- W3122473522 cites W2964150020 @default.
- W3122473522 cites W2964210007 @default.
- W3122473522 cites W2967591898 @default.
- W3122473522 cites W2969612742 @default.
- W3122473522 cites W2979679630 @default.
- W3122473522 cites W2994865335 @default.
- W3122473522 cites W2997915791 @default.
- W3122473522 cites W2998011150 @default.
- W3122473522 cites W2998907024 @default.
- W3122473522 cites W3000410628 @default.
- W3122473522 cites W3011348730 @default.
- W3122473522 cites W3012438487 @default.
- W3122473522 cites W3098605233 @default.
- W3122473522 cites W3100600242 @default.
- W3122473522 cites W3100698844 @default.
- W3122473522 cites W3101193405 @default.
- W3122473522 cites W3102072242 @default.
- W3122473522 cites W3104012431 @default.
- W3122473522 cites W3104423849 @default.
- W3122473522 cites W3105092369 @default.
- W3122473522 cites W3105867435 @default.
- W3122473522 cites W3121734253 @default.
- W3122473522 cites W3123680370 @default.
- W3122473522 cites W3146720657 @default.
- W3122473522 cites W4252684946 @default.
- W3122473522 cites W4288080275 @default.
- W3122473522 cites W4288614128 @default.
- W3122473522 cites W4289276777 @default.
- W3122473522 cites W841012168 @default.
- W3122473522 doi "https://doi.org/10.1145/3324884.3416532" @default.
- W3122473522 hasPublicationYear "2020" @default.
- W3122473522 type Work @default.
- W3122473522 sameAs 3122473522 @default.
- W3122473522 citedByCount "38" @default.
- W3122473522 countsByYear W31224735222021 @default.
- W3122473522 countsByYear W31224735222022 @default.
- W3122473522 countsByYear W31224735222023 @default.
- W3122473522 crossrefType "proceedings-article" @default.
- W3122473522 hasAuthorship W3122473522A5027475930 @default.
- W3122473522 hasAuthorship W3122473522A5035099591 @default.
- W3122473522 hasAuthorship W3122473522A5040326968 @default.
- W3122473522 hasAuthorship W3122473522A5050968170 @default.
- W3122473522 hasAuthorship W3122473522A5052007870 @default.
- W3122473522 hasAuthorship W3122473522A5070518954 @default.
- W3122473522 hasAuthorship W3122473522A5082835974 @default.
- W3122473522 hasBestOaLocation W31224735222 @default.
- W3122473522 hasConcept C104317684 @default.
- W3122473522 hasConcept C108583219 @default.
- W3122473522 hasConcept C111919701 @default.
- W3122473522 hasConcept C119857082 @default.
- W3122473522 hasConcept C127705205 @default.
- W3122473522 hasConcept C149091818 @default.
- W3122473522 hasConcept C154945302 @default.
- W3122473522 hasConcept C177264268 @default.
- W3122473522 hasConcept C17744445 @default.
- W3122473522 hasConcept C185592680 @default.