Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113471817> ?p ?o ?g. }
- W3113471817 abstract "Deep neural networks employ multiple processing layers for learning text representations to alleviate the burden of manual feature engineering in Natural Language Processing (NLP). Such text representations are widely used to extract features from unlabeled data. The word segmentation is a fundamental and inevitable prerequisite for many languages. Sindhi is an under-resourced language, whose segmentation is challenging as it exhibits space omission, space insertion issues, and lacks the labeled corpus for segmentation. In this paper, we investigate supervised Sindhi Word Segmentation (SWS) using unlabeled data with a Subword Guided Neural Word Segmenter (SGNWS) for Sindhi. In order to learn text representations, we incorporate subword representations to recurrent neural architecture to capture word information at morphemic-level, which takes advantage of Bidirectional Long-Short Term Memory (BiLSTM), self-attention mechanism, and Conditional Random Field (CRF). Our proposed SGNWS model achieves an F1 value of 98.51% without relying on feature engineering. The empirical results demonstrate the benefits of the proposed model over the existing Sindhi word segmenters." @default.
- W3113471817 created "2021-01-05" @default.
- W3113471817 creator A5016123311 @default.
- W3113471817 creator A5016649343 @default.
- W3113471817 creator A5041392292 @default.
- W3113471817 creator A5051227924 @default.
- W3113471817 creator A5055826974 @default.
- W3113471817 creator A5071564241 @default.
- W3113471817 creator A5072850680 @default.
- W3113471817 creator A5088843448 @default.
- W3113471817 date "2020-12-30" @default.
- W3113471817 modified "2023-10-14" @default.
- W3113471817 title "A Subword Guided Neural Word Segmentation Model for Sindhi." @default.
- W3113471817 cites W1815076433 @default.
- W3113471817 cites W1940872118 @default.
- W3113471817 cites W2064675550 @default.
- W3113471817 cites W2131774270 @default.
- W3113471817 cites W2143017621 @default.
- W3113471817 cites W2144639898 @default.
- W3113471817 cites W2147880316 @default.
- W3113471817 cites W2153579005 @default.
- W3113471817 cites W2158899491 @default.
- W3113471817 cites W2233994034 @default.
- W3113471817 cites W2250739653 @default.
- W3113471817 cites W2274880506 @default.
- W3113471817 cites W2398978578 @default.
- W3113471817 cites W2402144811 @default.
- W3113471817 cites W2423157849 @default.
- W3113471817 cites W2493916176 @default.
- W3113471817 cites W2611455120 @default.
- W3113471817 cites W2738180183 @default.
- W3113471817 cites W2742947407 @default.
- W3113471817 cites W2756999401 @default.
- W3113471817 cites W2761103884 @default.
- W3113471817 cites W2807812398 @default.
- W3113471817 cites W2824731080 @default.
- W3113471817 cites W2880875857 @default.
- W3113471817 cites W2889784708 @default.
- W3113471817 cites W2896649846 @default.
- W3113471817 cites W2900613036 @default.
- W3113471817 cites W2912165583 @default.
- W3113471817 cites W2962885853 @default.
- W3113471817 cites W2962987875 @default.
- W3113471817 cites W2963266340 @default.
- W3113471817 cites W2963403868 @default.
- W3113471817 cites W2963572611 @default.
- W3113471817 cites W2963748681 @default.
- W3113471817 cites W2963838731 @default.
- W3113471817 cites W2964093505 @default.
- W3113471817 cites W2966234499 @default.
- W3113471817 cites W2993091699 @default.
- W3113471817 cites W3004135517 @default.
- W3113471817 cites W3113915881 @default.
- W3113471817 cites W2587051312 @default.
- W3113471817 hasPublicationYear "2020" @default.
- W3113471817 type Work @default.
- W3113471817 sameAs 3113471817 @default.
- W3113471817 citedByCount "1" @default.
- W3113471817 countsByYear W31134718172021 @default.
- W3113471817 crossrefType "posted-content" @default.
- W3113471817 hasAuthorship W3113471817A5016123311 @default.
- W3113471817 hasAuthorship W3113471817A5016649343 @default.
- W3113471817 hasAuthorship W3113471817A5041392292 @default.
- W3113471817 hasAuthorship W3113471817A5051227924 @default.
- W3113471817 hasAuthorship W3113471817A5055826974 @default.
- W3113471817 hasAuthorship W3113471817A5071564241 @default.
- W3113471817 hasAuthorship W3113471817A5072850680 @default.
- W3113471817 hasAuthorship W3113471817A5088843448 @default.
- W3113471817 hasConcept C108583219 @default.
- W3113471817 hasConcept C111919701 @default.
- W3113471817 hasConcept C138885662 @default.
- W3113471817 hasConcept C152565575 @default.
- W3113471817 hasConcept C153180895 @default.
- W3113471817 hasConcept C154945302 @default.
- W3113471817 hasConcept C165297611 @default.
- W3113471817 hasConcept C204321447 @default.
- W3113471817 hasConcept C2524010 @default.
- W3113471817 hasConcept C2776401178 @default.
- W3113471817 hasConcept C2778572836 @default.
- W3113471817 hasConcept C2778827112 @default.
- W3113471817 hasConcept C28490314 @default.
- W3113471817 hasConcept C33923547 @default.
- W3113471817 hasConcept C41008148 @default.
- W3113471817 hasConcept C41895202 @default.
- W3113471817 hasConcept C50644808 @default.
- W3113471817 hasConcept C89600930 @default.
- W3113471817 hasConcept C90805587 @default.
- W3113471817 hasConcept C98501671 @default.
- W3113471817 hasConceptScore W3113471817C108583219 @default.
- W3113471817 hasConceptScore W3113471817C111919701 @default.
- W3113471817 hasConceptScore W3113471817C138885662 @default.
- W3113471817 hasConceptScore W3113471817C152565575 @default.
- W3113471817 hasConceptScore W3113471817C153180895 @default.
- W3113471817 hasConceptScore W3113471817C154945302 @default.
- W3113471817 hasConceptScore W3113471817C165297611 @default.
- W3113471817 hasConceptScore W3113471817C204321447 @default.
- W3113471817 hasConceptScore W3113471817C2524010 @default.
- W3113471817 hasConceptScore W3113471817C2776401178 @default.
- W3113471817 hasConceptScore W3113471817C2778572836 @default.
- W3113471817 hasConceptScore W3113471817C2778827112 @default.