Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204509034> ?p ?o ?g. }
- W3204509034 abstract "In this paper, we propose a span labeling approach to model n-gram information for Vietnamese word segmentation, namely SPAN SEG. We compare the span labeling approach with the conditional random field by using encoders with the same architecture. Since Vietnamese and Chinese have similar linguistic phenomena, we evaluated the proposed method on the Vietnamese treebank benchmark dataset and five Chinese benchmark datasets. Through our experimental results, the proposed approach SpanSeg achieves higher performance than the sequence tagging approach with the state-of-the-art F-score of 98.31% on the Vietnamese treebank benchmark, when they both apply the contextual pre-trained language model XLM-RoBERTa and the predicted word boundary information. Besides, we do fine-tuning experiments for the span labeling approach on BERT and ZEN pre-trained language model for Chinese with fewer parameters, faster inference time, and competitive or higher F-scores than the previous state-of-the-art approach, word segmentation with word-hood memory networks, on five Chinese benchmarks." @default.
- W3204509034 created "2021-10-11" @default.
- W3204509034 creator A5000998116 @default.
- W3204509034 creator A5009894498 @default.
- W3204509034 creator A5033137339 @default.
- W3204509034 creator A5050764993 @default.
- W3204509034 date "2021-10-01" @default.
- W3204509034 modified "2023-09-27" @default.
- W3204509034 title "Span Labeling Approach for Vietnamese and Chinese Word Segmentation." @default.
- W3204509034 cites W1757859293 @default.
- W3204509034 cites W1977877104 @default.
- W3204509034 cites W2096204319 @default.
- W3204509034 cites W2142263282 @default.
- W3204509034 cites W2250739653 @default.
- W3204509034 cites W2251271075 @default.
- W3204509034 cites W2467575451 @default.
- W3204509034 cites W25062297 @default.
- W3204509034 cites W2507296208 @default.
- W3204509034 cites W2516334389 @default.
- W3204509034 cites W2563544594 @default.
- W3204509034 cites W2757350179 @default.
- W3204509034 cites W27634986 @default.
- W3204509034 cites W2903674902 @default.
- W3204509034 cites W2908510526 @default.
- W3204509034 cites W2945864679 @default.
- W3204509034 cites W2962885853 @default.
- W3204509034 cites W2963341956 @default.
- W3204509034 cites W2963355640 @default.
- W3204509034 cites W2963571341 @default.
- W3204509034 cites W2963841919 @default.
- W3204509034 cites W2964030814 @default.
- W3204509034 cites W2964336292 @default.
- W3204509034 cites W3004142601 @default.
- W3204509034 cites W3035193825 @default.
- W3204509034 cites W3035390927 @default.
- W3204509034 cites W3046268331 @default.
- W3204509034 cites W3098065087 @default.
- W3204509034 cites W3101805561 @default.
- W3204509034 cites W3102085674 @default.
- W3204509034 hasPublicationYear "2021" @default.
- W3204509034 type Work @default.
- W3204509034 sameAs 3204509034 @default.
- W3204509034 citedByCount "0" @default.
- W3204509034 crossrefType "posted-content" @default.
- W3204509034 hasAuthorship W3204509034A5000998116 @default.
- W3204509034 hasAuthorship W3204509034A5009894498 @default.
- W3204509034 hasAuthorship W3204509034A5033137339 @default.
- W3204509034 hasAuthorship W3204509034A5050764993 @default.
- W3204509034 hasConcept C103621254 @default.
- W3204509034 hasConcept C111919701 @default.
- W3204509034 hasConcept C118505674 @default.
- W3204509034 hasConcept C127413603 @default.
- W3204509034 hasConcept C13280743 @default.
- W3204509034 hasConcept C138885662 @default.
- W3204509034 hasConcept C147176958 @default.
- W3204509034 hasConcept C152565575 @default.
- W3204509034 hasConcept C154945302 @default.
- W3204509034 hasConcept C162324750 @default.
- W3204509034 hasConcept C185798385 @default.
- W3204509034 hasConcept C186644900 @default.
- W3204509034 hasConcept C187736073 @default.
- W3204509034 hasConcept C204321447 @default.
- W3204509034 hasConcept C205649164 @default.
- W3204509034 hasConcept C206134035 @default.
- W3204509034 hasConcept C2776214188 @default.
- W3204509034 hasConcept C2778753569 @default.
- W3204509034 hasConcept C2779135771 @default.
- W3204509034 hasConcept C2780451532 @default.
- W3204509034 hasConcept C28490314 @default.
- W3204509034 hasConcept C35639132 @default.
- W3204509034 hasConcept C41008148 @default.
- W3204509034 hasConcept C41895202 @default.
- W3204509034 hasConcept C89600930 @default.
- W3204509034 hasConcept C90805587 @default.
- W3204509034 hasConcept C98501671 @default.
- W3204509034 hasConceptScore W3204509034C103621254 @default.
- W3204509034 hasConceptScore W3204509034C111919701 @default.
- W3204509034 hasConceptScore W3204509034C118505674 @default.
- W3204509034 hasConceptScore W3204509034C127413603 @default.
- W3204509034 hasConceptScore W3204509034C13280743 @default.
- W3204509034 hasConceptScore W3204509034C138885662 @default.
- W3204509034 hasConceptScore W3204509034C147176958 @default.
- W3204509034 hasConceptScore W3204509034C152565575 @default.
- W3204509034 hasConceptScore W3204509034C154945302 @default.
- W3204509034 hasConceptScore W3204509034C162324750 @default.
- W3204509034 hasConceptScore W3204509034C185798385 @default.
- W3204509034 hasConceptScore W3204509034C186644900 @default.
- W3204509034 hasConceptScore W3204509034C187736073 @default.
- W3204509034 hasConceptScore W3204509034C204321447 @default.
- W3204509034 hasConceptScore W3204509034C205649164 @default.
- W3204509034 hasConceptScore W3204509034C206134035 @default.
- W3204509034 hasConceptScore W3204509034C2776214188 @default.
- W3204509034 hasConceptScore W3204509034C2778753569 @default.
- W3204509034 hasConceptScore W3204509034C2779135771 @default.
- W3204509034 hasConceptScore W3204509034C2780451532 @default.
- W3204509034 hasConceptScore W3204509034C28490314 @default.
- W3204509034 hasConceptScore W3204509034C35639132 @default.
- W3204509034 hasConceptScore W3204509034C41008148 @default.
- W3204509034 hasConceptScore W3204509034C41895202 @default.
- W3204509034 hasConceptScore W3204509034C89600930 @default.