FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994865335> ?p ?o ?g. }

• W2994865335 abstract "Many Natural Language Processing (NLP) tasks, such as sentiment analysis or syntactic parsing, have benefited from the development of word embedding models. In particular, regardless of the training algorithms, the learned embeddings have often been shown to be generalizable to different NLP tasks. In contrast, despite recent momentum on word embeddings for source code, the literature lacks evidence of their generalizability beyond the example task they have been trained for. In this experience paper, we identify 3 potential downstream tasks, namely code comments generation, code authorship identification, and code clones detection, that source code token embedding models can be applied to. We empirically assess a recently proposed code token embedding model, namely code2vec's token embeddings. Code2vec was trained on the task of predicting method names, and while there is potential for using the vectors it learns on other tasks, it has not been explored in literature. Therefore, we fill this gap by focusing on its generalizability for the tasks we have identified. Eventually, we show that source code token embeddings cannot be readily leveraged for the downstream tasks. Our experiments even show that our attempts to use them do not result in any improvements over less sophisticated methods. We call for more research into effective and general use of code embeddings." @default.
• W2994865335 created "2019-12-26" @default.
• W2994865335 creator A5027335548 @default.
• W2994865335 creator A5081036622 @default.
• W2994865335 creator A5082835974 @default.
• W2994865335 date "2019-11-01" @default.
• W2994865335 modified "2023-10-16" @default.
• W2994865335 title "Assessing the Generalizability of Code2vec Token Embeddings" @default.
• W2994865335 cites W1698439592 @default.
• W2994865335 cites W2010608861 @default.
• W2994865335 cites W2013638584 @default.
• W2994865335 cites W2018890516 @default.
• W2994865335 cites W2064675550 @default.
• W2994865335 cites W2065053490 @default.
• W2994865335 cites W2082160726 @default.
• W2994865335 cites W2117130368 @default.
• W2994865335 cites W2118548380 @default.
• W2994865335 cites W2136296681 @default.
• W2994865335 cites W2139270835 @default.
• W2994865335 cites W2154151876 @default.
• W2994865335 cites W2156981320 @default.
• W2994865335 cites W2158439356 @default.
• W2994865335 cites W2250539671 @default.
• W2994865335 cites W2252211741 @default.
• W2994865335 cites W2282866165 @default.
• W2994865335 cites W2401290433 @default.
• W2994865335 cites W2402619042 @default.
• W2994865335 cites W2516621648 @default.
• W2994865335 cites W2518202280 @default.
• W2994865335 cites W2736762043 @default.
• W2994865335 cites W2740130862 @default.
• W2994865335 cites W2794601162 @default.
• W2994865335 cites W2806718802 @default.
• W2994865335 cites W2808509424 @default.
• W2994865335 cites W2884276923 @default.
• W2994865335 cites W2888312537 @default.
• W2994865335 cites W2891865791 @default.
• W2994865335 cites W2899384793 @default.
• W2994865335 cites W2917037155 @default.
• W2994865335 cites W2922006620 @default.
• W2994865335 cites W2938075706 @default.
• W2994865335 cites W2962894772 @default.
• W2994865335 cites W2963055550 @default.
• W2994865335 cites W2963212250 @default.
• W2994865335 cites W2963419157 @default.
• W2994865335 cites W2964150020 @default.
• W2994865335 cites W2964322208 @default.
• W2994865335 cites W3005951744 @default.
• W2994865335 cites W3099095494 @default.
• W2994865335 cites W3104712907 @default.
• W2994865335 cites W3105535951 @default.
• W2994865335 cites W3105926539 @default.
• W2994865335 cites W3146720657 @default.
• W2994865335 cites W4233322385 @default.
• W2994865335 cites W4250089123 @default.
• W2994865335 cites W4301168982 @default.
• W2994865335 doi "https://doi.org/10.1109/ase.2019.00011" @default.
• W2994865335 hasPublicationYear "2019" @default.
• W2994865335 type Work @default.
• W2994865335 sameAs 2994865335 @default.
• W2994865335 citedByCount "48" @default.
• W2994865335 countsByYear W29948653352019 @default.
• W2994865335 countsByYear W29948653352020 @default.
• W2994865335 countsByYear W29948653352021 @default.
• W2994865335 countsByYear W29948653352022 @default.
• W2994865335 countsByYear W29948653352023 @default.
• W2994865335 crossrefType "proceedings-article" @default.
• W2994865335 hasAuthorship W2994865335A5027335548 @default.
• W2994865335 hasAuthorship W2994865335A5081036622 @default.
• W2994865335 hasAuthorship W2994865335A5082835974 @default.
• W2994865335 hasBestOaLocation W29948653352 @default.
• W2994865335 hasConcept C116834253 @default.
• W2994865335 hasConcept C119857082 @default.
• W2994865335 hasConcept C138496976 @default.
• W2994865335 hasConcept C138885662 @default.
• W2994865335 hasConcept C154945302 @default.
• W2994865335 hasConcept C15744967 @default.
• W2994865335 hasConcept C162324750 @default.
• W2994865335 hasConcept C177264268 @default.
• W2994865335 hasConcept C186644900 @default.
• W2994865335 hasConcept C187736073 @default.
• W2994865335 hasConcept C199360897 @default.
• W2994865335 hasConcept C204321447 @default.
• W2994865335 hasConcept C27158222 @default.
• W2994865335 hasConcept C2776760102 @default.
• W2994865335 hasConcept C2777462759 @default.
• W2994865335 hasConcept C2780451532 @default.
• W2994865335 hasConcept C38652104 @default.
• W2994865335 hasConcept C41008148 @default.
• W2994865335 hasConcept C41608201 @default.
• W2994865335 hasConcept C41895202 @default.
• W2994865335 hasConcept C43126263 @default.
• W2994865335 hasConcept C48145219 @default.
• W2994865335 hasConcept C59822182 @default.
• W2994865335 hasConcept C86803240 @default.
• W2994865335 hasConcept C90805587 @default.
• W2994865335 hasConceptScore W2994865335C116834253 @default.
• W2994865335 hasConceptScore W2994865335C119857082 @default.
• W2994865335 hasConceptScore W2994865335C138496976 @default.
• W2994865335 hasConceptScore W2994865335C138885662 @default.

• next