Matches in SemOpenAlex for { <https://semopenalex.org/work/W2020757772> ?p ?o ?g. }
- W2020757772 abstract "In this paper, we propose the use of distance and co-occurrence information of word-pairs to improve language modeling. We have empirically shown that, for history-context sizes of up to ten words, the extracted information about distance and co-occurrence complements the n-gram language model well, for which learning long-history contexts is inherently difficult. Evaluated on the Wall Street Journal and the Switchboard corpora, our proposed model reduces the trigram model perplexity by up to 11.2% and 6.5%, respectively. As compared to the distant bigram model and the trigger model, our proposed model offers a more effective manner of capturing far context information, as verified in terms of perplexity and computational efficiency, i.e., fewer free parameters to be fine-tuned. Experiments using the proposed model for speech recognition, text classification and word prediction tasks showed improved performance." @default.
- W2020757772 created "2016-06-24" @default.
- W2020757772 creator A5001136890 @default.
- W2020757772 creator A5022050902 @default.
- W2020757772 creator A5032690182 @default.
- W2020757772 creator A5070872826 @default.
- W2020757772 date "2015-07-01" @default.
- W2020757772 modified "2023-09-25" @default.
- W2020757772 title "Decoupling Word-Pair Distance and Co-occurrence Information for Effective Long History Context Language Modeling" @default.
- W2020757772 cites W1492775261 @default.
- W2020757772 cites W157257245 @default.
- W2020757772 cites W1593045043 @default.
- W2020757772 cites W1665921526 @default.
- W2020757772 cites W1791847295 @default.
- W2020757772 cites W1904722842 @default.
- W2020757772 cites W1916806189 @default.
- W2020757772 cites W1966812932 @default.
- W2020757772 cites W1970689298 @default.
- W2020757772 cites W1975422446 @default.
- W2020757772 cites W1989705153 @default.
- W2020757772 cites W1996903695 @default.
- W2020757772 cites W2013196554 @default.
- W2020757772 cites W2019165876 @default.
- W2020757772 cites W2026430321 @default.
- W2020757772 cites W2057384730 @default.
- W2020757772 cites W2078549297 @default.
- W2020757772 cites W2102439588 @default.
- W2020757772 cites W2103277165 @default.
- W2020757772 cites W2104404542 @default.
- W2020757772 cites W2110027950 @default.
- W2020757772 cites W2114524997 @default.
- W2020757772 cites W2117423052 @default.
- W2020757772 cites W2119907552 @default.
- W2020757772 cites W2120587055 @default.
- W2020757772 cites W2124008567 @default.
- W2020757772 cites W2127836646 @default.
- W2020757772 cites W2131462252 @default.
- W2020757772 cites W2132339004 @default.
- W2020757772 cites W2166706824 @default.
- W2020757772 cites W2168322422 @default.
- W2020757772 cites W2171330477 @default.
- W2020757772 cites W2171343311 @default.
- W2020757772 cites W2171645516 @default.
- W2020757772 cites W2171928131 @default.
- W2020757772 cites W2250909759 @default.
- W2020757772 cites W2311893701 @default.
- W2020757772 cites W2399839020 @default.
- W2020757772 cites W2759336060 @default.
- W2020757772 cites W2950186769 @default.
- W2020757772 cites W36903255 @default.
- W2020757772 cites W57814663 @default.
- W2020757772 cites W62865938 @default.
- W2020757772 cites W67002875 @default.
- W2020757772 cites W92274471 @default.
- W2020757772 cites W943204654 @default.
- W2020757772 cites W98731357 @default.
- W2020757772 doi "https://doi.org/10.1109/taslp.2015.2425223" @default.
- W2020757772 hasPublicationYear "2015" @default.
- W2020757772 type Work @default.
- W2020757772 sameAs 2020757772 @default.
- W2020757772 citedByCount "1" @default.
- W2020757772 countsByYear W20207577722018 @default.
- W2020757772 crossrefType "journal-article" @default.
- W2020757772 hasAuthorship W2020757772A5001136890 @default.
- W2020757772 hasAuthorship W2020757772A5022050902 @default.
- W2020757772 hasAuthorship W2020757772A5032690182 @default.
- W2020757772 hasAuthorship W2020757772A5070872826 @default.
- W2020757772 hasConcept C100279451 @default.
- W2020757772 hasConcept C108757681 @default.
- W2020757772 hasConcept C117884012 @default.
- W2020757772 hasConcept C127413603 @default.
- W2020757772 hasConcept C133731056 @default.
- W2020757772 hasConcept C137293760 @default.
- W2020757772 hasConcept C137546455 @default.
- W2020757772 hasConcept C138885662 @default.
- W2020757772 hasConcept C151730666 @default.
- W2020757772 hasConcept C154945302 @default.
- W2020757772 hasConcept C183322885 @default.
- W2020757772 hasConcept C204321447 @default.
- W2020757772 hasConcept C205606062 @default.
- W2020757772 hasConcept C2779343474 @default.
- W2020757772 hasConcept C2781238097 @default.
- W2020757772 hasConcept C28490314 @default.
- W2020757772 hasConcept C41008148 @default.
- W2020757772 hasConcept C41895202 @default.
- W2020757772 hasConcept C86803240 @default.
- W2020757772 hasConcept C90805587 @default.
- W2020757772 hasConceptScore W2020757772C100279451 @default.
- W2020757772 hasConceptScore W2020757772C108757681 @default.
- W2020757772 hasConceptScore W2020757772C117884012 @default.
- W2020757772 hasConceptScore W2020757772C127413603 @default.
- W2020757772 hasConceptScore W2020757772C133731056 @default.
- W2020757772 hasConceptScore W2020757772C137293760 @default.
- W2020757772 hasConceptScore W2020757772C137546455 @default.
- W2020757772 hasConceptScore W2020757772C138885662 @default.
- W2020757772 hasConceptScore W2020757772C151730666 @default.
- W2020757772 hasConceptScore W2020757772C154945302 @default.
- W2020757772 hasConceptScore W2020757772C183322885 @default.
- W2020757772 hasConceptScore W2020757772C204321447 @default.
- W2020757772 hasConceptScore W2020757772C205606062 @default.