FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2740130862> ?p ?o ?g. }

• W2740130862 abstract "Current statistical language modeling techniques, including deep-learning based models, have proven to be quite effective for source code. We argue here that the special properties of source code can be exploited for further improvements. In this work, we enhance established language modeling approaches to handle the special challenges of modeling source code, such as: frequent changes, larger, changing vocabularies, deeply nested scopes, etc. We present a fast, nested language modeling toolkit specifically designed for software, with the ability to add & remove text, and mix & swap out many models. Specifically, we improve upon prior cache-modeling work and present a model with a much more expansive, multi-level notion of locality that we show to be well-suited for modeling software. We present results on varying corpora in comparison with traditional N-gram, as well as RNN, and LSTM deep-learning language models, and release all our source code for public use. Our evaluations suggest that carefully adapting N-gram models for source code can yield performance that surpasses even RNN and LSTM based deep-learning models." @default.
• W2740130862 created "2017-08-08" @default.
• W2740130862 creator A5009679905 @default.
• W2740130862 creator A5036744986 @default.
• W2740130862 date "2017-08-21" @default.
• W2740130862 modified "2023-09-29" @default.
• W2740130862 title "Are deep neural networks the best choice for modeling source code?" @default.
• W2740130862 cites W1607229519 @default.
• W2740130862 cites W1655078475 @default.
• W2740130862 cites W1771830246 @default.
• W2740130862 cites W1970607969 @default.
• W2740130862 cites W1972141422 @default.
• W2740130862 cites W1974020522 @default.
• W2740130862 cites W1994573369 @default.
• W2740130862 cites W2060384944 @default.
• W2740130862 cites W2064675550 @default.
• W2740130862 cites W2066714497 @default.
• W2740130862 cites W2074032109 @default.
• W2740130862 cites W2083878868 @default.
• W2740130862 cites W2097927681 @default.
• W2740130862 cites W2140609933 @default.
• W2740130862 cites W2142403498 @default.
• W2740130862 cites W2165747537 @default.
• W2740130862 cites W2166597811 @default.
• W2740130862 cites W2511803001 @default.
• W2740130862 cites W2547880329 @default.
• W2740130862 cites W3005855585 @default.
• W2740130862 cites W3021713638 @default.
• W2740130862 cites W3104874136 @default.
• W2740130862 doi "https://doi.org/10.1145/3106237.3106290" @default.
• W2740130862 hasPublicationYear "2017" @default.
• W2740130862 type Work @default.
• W2740130862 sameAs 2740130862 @default.
• W2740130862 citedByCount "221" @default.
• W2740130862 countsByYear W27401308622017 @default.
• W2740130862 countsByYear W27401308622018 @default.
• W2740130862 countsByYear W27401308622019 @default.
• W2740130862 countsByYear W27401308622020 @default.
• W2740130862 countsByYear W27401308622021 @default.
• W2740130862 countsByYear W27401308622022 @default.
• W2740130862 countsByYear W27401308622023 @default.
• W2740130862 crossrefType "proceedings-article" @default.
• W2740130862 hasAuthorship W2740130862A5009679905 @default.
• W2740130862 hasAuthorship W2740130862A5036744986 @default.
• W2740130862 hasConcept C108583219 @default.
• W2740130862 hasConcept C115537543 @default.
• W2740130862 hasConcept C117884012 @default.
• W2740130862 hasConcept C119857082 @default.
• W2740130862 hasConcept C137293760 @default.
• W2740130862 hasConcept C138885662 @default.
• W2740130862 hasConcept C154945302 @default.
• W2740130862 hasConcept C173608175 @default.
• W2740130862 hasConcept C177264268 @default.
• W2740130862 hasConcept C179603123 @default.
• W2740130862 hasConcept C199360897 @default.
• W2740130862 hasConcept C204321447 @default.
• W2740130862 hasConcept C27602214 @default.
• W2740130862 hasConcept C2776760102 @default.
• W2740130862 hasConcept C2777904410 @default.
• W2740130862 hasConcept C2779808786 @default.
• W2740130862 hasConcept C41008148 @default.
• W2740130862 hasConcept C41895202 @default.
• W2740130862 hasConcept C43126263 @default.
• W2740130862 hasConcept C51929080 @default.
• W2740130862 hasConceptScore W2740130862C108583219 @default.
• W2740130862 hasConceptScore W2740130862C115537543 @default.
• W2740130862 hasConceptScore W2740130862C117884012 @default.
• W2740130862 hasConceptScore W2740130862C119857082 @default.
• W2740130862 hasConceptScore W2740130862C137293760 @default.
• W2740130862 hasConceptScore W2740130862C138885662 @default.
• W2740130862 hasConceptScore W2740130862C154945302 @default.
• W2740130862 hasConceptScore W2740130862C173608175 @default.
• W2740130862 hasConceptScore W2740130862C177264268 @default.
• W2740130862 hasConceptScore W2740130862C179603123 @default.
• W2740130862 hasConceptScore W2740130862C199360897 @default.
• W2740130862 hasConceptScore W2740130862C204321447 @default.
• W2740130862 hasConceptScore W2740130862C27602214 @default.
• W2740130862 hasConceptScore W2740130862C2776760102 @default.
• W2740130862 hasConceptScore W2740130862C2777904410 @default.
• W2740130862 hasConceptScore W2740130862C2779808786 @default.
• W2740130862 hasConceptScore W2740130862C41008148 @default.
• W2740130862 hasConceptScore W2740130862C41895202 @default.
• W2740130862 hasConceptScore W2740130862C43126263 @default.
• W2740130862 hasConceptScore W2740130862C51929080 @default.
• W2740130862 hasFunder F4320306076 @default.
• W2740130862 hasLocation W27401308621 @default.
• W2740130862 hasOpenAccess W2740130862 @default.
• W2740130862 hasPrimaryLocation W27401308621 @default.
• W2740130862 hasRelatedWork W1479933889 @default.
• W2740130862 hasRelatedWork W1522113126 @default.
• W2740130862 hasRelatedWork W1554690752 @default.
• W2740130862 hasRelatedWork W1808157093 @default.
• W2740130862 hasRelatedWork W2013531410 @default.
• W2740130862 hasRelatedWork W2135396778 @default.
• W2740130862 hasRelatedWork W2290683570 @default.
• W2740130862 hasRelatedWork W283806354 @default.
• W2740130862 hasRelatedWork W4233387348 @default.
• W2740130862 hasRelatedWork W4243312585 @default.
• W2740130862 isParatext "false" @default.
• W2740130862 isRetracted "false" @default.

• next