FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165364314> ?p ?o ?g. }

• W3165364314 endingPage "25" @default.
• W3165364314 startingPage "1" @default.
• W3165364314 abstract "The need to capture intra-word information in natural language processing (NLP) tasks has inspired research in learning various word representations at word, character, or morpheme levels, but little attention has been given to syllables from a syllabic alphabet. Motivated by the success of compositional models in morphological languages, we present a Convolutional-long short term memory (Conv-LSTM) model for constructing Swahili word representation vectors from syllables. The unified architecture addresses the word agglutination and polysemous nature of Swahili by extracting high-level syllable features using a convolutional neural network (CNN) and then composes quality word embeddings with a long short term memory (LSTM). The word embeddings are then validated using a syllable-aware language model ( 31.267 ) and a part-of-speech (POS) tagging task ( 98.78 ), both yielding very competitive results to the state-of-art models in their respective domains. We further validate the language model using Xhosa and Shona, which are syllabic-based languages. The novelty of the study is in its capability to construct quality word embeddings from syllables using a hybrid model that does not use max-over-pool common in CNN and then the exploitation of these embeddings in POS tagging. Therefore, the study plays a crucial role in the processing of agglutinative and syllabic-based languages by contributing quality word embeddings from syllable embeddings, a robust Conv–LSTM model that learns syllables for not only language modeling and POS tagging, but also for other downstream NLP tasks." @default.
• W3165364314 created "2021-06-07" @default.
• W3165364314 creator A5012385922 @default.
• W3165364314 creator A5073705151 @default.
• W3165364314 creator A5075954010 @default.
• W3165364314 creator A5078963412 @default.
• W3165364314 date "2021-05-26" @default.
• W3165364314 modified "2023-09-29" @default.
• W3165364314 title "Learning Syllables Using Conv-LSTM Model for Swahili Word Representation and Part-of-speech Tagging" @default.
• W3165364314 cites W1584393767 @default.
• W3165364314 cites W1899794420 @default.
• W3165364314 cites W1905882502 @default.
• W3165364314 cites W1984426124 @default.
• W3165364314 cites W1995341919 @default.
• W3165364314 cites W2064675550 @default.
• W3165364314 cites W2077566853 @default.
• W3165364314 cites W2110485445 @default.
• W3165364314 cites W2117130368 @default.
• W3165364314 cites W2131774270 @default.
• W3165364314 cites W2142384583 @default.
• W3165364314 cites W2157331557 @default.
• W3165364314 cites W2167646176 @default.
• W3165364314 cites W2186845332 @default.
• W3165364314 cites W2250539671 @default.
• W3165364314 cites W2343954916 @default.
• W3165364314 cites W2417763662 @default.
• W3165364314 cites W2463895987 @default.
• W3165364314 cites W2493916176 @default.
• W3165364314 cites W2740144049 @default.
• W3165364314 cites W2740646860 @default.
• W3165364314 cites W2791521493 @default.
• W3165364314 cites W2884001105 @default.
• W3165364314 cites W2886167250 @default.
• W3165364314 cites W2891680269 @default.
• W3165364314 cites W2908092214 @default.
• W3165364314 cites W2916755661 @default.
• W3165364314 cites W2939808777 @default.
• W3165364314 cites W2942573273 @default.
• W3165364314 cites W2963099225 @default.
• W3165364314 cites W2963402126 @default.
• W3165364314 cites W2964005834 @default.
• W3165364314 cites W2964234219 @default.
• W3165364314 cites W2972161408 @default.
• W3165364314 cites W2984250044 @default.
• W3165364314 cites W2989576650 @default.
• W3165364314 cites W2997617958 @default.
• W3165364314 cites W2998704965 @default.
• W3165364314 cites W3035784317 @default.
• W3165364314 cites W3101124347 @default.
• W3165364314 doi "https://doi.org/10.1145/3445975" @default.
• W3165364314 hasPublicationYear "2021" @default.
• W3165364314 type Work @default.
• W3165364314 sameAs 3165364314 @default.
• W3165364314 citedByCount "2" @default.
• W3165364314 countsByYear W31653643142023 @default.
• W3165364314 crossrefType "journal-article" @default.
• W3165364314 hasAuthorship W3165364314A5012385922 @default.
• W3165364314 hasAuthorship W3165364314A5073705151 @default.
• W3165364314 hasAuthorship W3165364314A5075954010 @default.
• W3165364314 hasAuthorship W3165364314A5078963412 @default.
• W3165364314 hasConcept C109089402 @default.
• W3165364314 hasConcept C137293760 @default.
• W3165364314 hasConcept C138885662 @default.
• W3165364314 hasConcept C154945302 @default.
• W3165364314 hasConcept C165297611 @default.
• W3165364314 hasConcept C194051139 @default.
• W3165364314 hasConcept C204321447 @default.
• W3165364314 hasConcept C2779913364 @default.
• W3165364314 hasConcept C28490314 @default.
• W3165364314 hasConcept C41008148 @default.
• W3165364314 hasConcept C41895202 @default.
• W3165364314 hasConcept C80875076 @default.
• W3165364314 hasConcept C90805587 @default.
• W3165364314 hasConceptScore W3165364314C109089402 @default.
• W3165364314 hasConceptScore W3165364314C137293760 @default.
• W3165364314 hasConceptScore W3165364314C138885662 @default.
• W3165364314 hasConceptScore W3165364314C154945302 @default.
• W3165364314 hasConceptScore W3165364314C165297611 @default.
• W3165364314 hasConceptScore W3165364314C194051139 @default.
• W3165364314 hasConceptScore W3165364314C204321447 @default.
• W3165364314 hasConceptScore W3165364314C2779913364 @default.
• W3165364314 hasConceptScore W3165364314C28490314 @default.
• W3165364314 hasConceptScore W3165364314C41008148 @default.
• W3165364314 hasConceptScore W3165364314C41895202 @default.
• W3165364314 hasConceptScore W3165364314C80875076 @default.
• W3165364314 hasConceptScore W3165364314C90805587 @default.
• W3165364314 hasFunder F4320335564 @default.
• W3165364314 hasIssue "4" @default.
• W3165364314 hasLocation W31653643141 @default.
• W3165364314 hasOpenAccess W3165364314 @default.
• W3165364314 hasPrimaryLocation W31653643141 @default.
• W3165364314 hasRelatedWork W1496925889 @default.
• W3165364314 hasRelatedWork W2165286282 @default.
• W3165364314 hasRelatedWork W2167715705 @default.
• W3165364314 hasRelatedWork W2480617478 @default.
• W3165364314 hasRelatedWork W2538341397 @default.
• W3165364314 hasRelatedWork W2562531466 @default.
• W3165364314 hasRelatedWork W2750090971 @default.

• next