Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386207844> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4386207844 abstract "Chinese text matching is an important task in natural language processing research, but the current techniques have problems in text feature extraction, such as insufficient word information extraction and lack of deep information in graph convolution networks. In this paper, we propose a model MFG-R for Chinese text matching with multi-information fusion graph embedding and residual connection. The model fuses the word embedding representation of the text obtained by graph convolution network with character-level information and word weight information to extract text features. At the same time, in order to perform deep interaction matching, we construct a word-level similarity interaction matrix between text pairs, and build a text interaction and feature extraction model based on residual network on this basis. Experiments show that MFG-R has excellent performance on two common Chinese datasets, Ant Financial Question Matching Corpus(AFQMC) and Large-scale Chinese Question Matching Corpus(LCQMC)." @default.
- W4386207844 created "2023-08-28" @default.
- W4386207844 creator A5042298145 @default.
- W4386207844 creator A5056747983 @default.
- W4386207844 creator A5056857939 @default.
- W4386207844 creator A5058637832 @default.
- W4386207844 creator A5070528488 @default.
- W4386207844 date "2023-07-09" @default.
- W4386207844 modified "2023-10-17" @default.
- W4386207844 title "MFG-R: Chinese Text Matching with Multi-Information Fusion Graph Embedding and Residual Connections" @default.
- W4386207844 cites W2123442489 @default.
- W4386207844 cites W2265289447 @default.
- W4386207844 cites W2593833795 @default.
- W4386207844 cites W2608787653 @default.
- W4386207844 cites W2953075226 @default.
- W4386207844 cites W2964082993 @default.
- W4386207844 cites W2971279399 @default.
- W4386207844 cites W2972073841 @default.
- W4386207844 cites W3034353423 @default.
- W4386207844 cites W3034438872 @default.
- W4386207844 cites W3035490055 @default.
- W4386207844 cites W3173220653 @default.
- W4386207844 cites W4223608052 @default.
- W4386207844 cites W4385573160 @default.
- W4386207844 doi "https://doi.org/10.1109/iscc58397.2023.10217835" @default.
- W4386207844 hasPublicationYear "2023" @default.
- W4386207844 type Work @default.
- W4386207844 citedByCount "0" @default.
- W4386207844 crossrefType "proceedings-article" @default.
- W4386207844 hasAuthorship W4386207844A5042298145 @default.
- W4386207844 hasAuthorship W4386207844A5056747983 @default.
- W4386207844 hasAuthorship W4386207844A5056857939 @default.
- W4386207844 hasAuthorship W4386207844A5058637832 @default.
- W4386207844 hasAuthorship W4386207844A5070528488 @default.
- W4386207844 hasConcept C105795698 @default.
- W4386207844 hasConcept C11413529 @default.
- W4386207844 hasConcept C132525143 @default.
- W4386207844 hasConcept C154945302 @default.
- W4386207844 hasConcept C155512373 @default.
- W4386207844 hasConcept C165064840 @default.
- W4386207844 hasConcept C204321447 @default.
- W4386207844 hasConcept C2777462759 @default.
- W4386207844 hasConcept C33923547 @default.
- W4386207844 hasConcept C41008148 @default.
- W4386207844 hasConcept C41608201 @default.
- W4386207844 hasConcept C52622490 @default.
- W4386207844 hasConcept C66945725 @default.
- W4386207844 hasConcept C71472368 @default.
- W4386207844 hasConcept C80444323 @default.
- W4386207844 hasConceptScore W4386207844C105795698 @default.
- W4386207844 hasConceptScore W4386207844C11413529 @default.
- W4386207844 hasConceptScore W4386207844C132525143 @default.
- W4386207844 hasConceptScore W4386207844C154945302 @default.
- W4386207844 hasConceptScore W4386207844C155512373 @default.
- W4386207844 hasConceptScore W4386207844C165064840 @default.
- W4386207844 hasConceptScore W4386207844C204321447 @default.
- W4386207844 hasConceptScore W4386207844C2777462759 @default.
- W4386207844 hasConceptScore W4386207844C33923547 @default.
- W4386207844 hasConceptScore W4386207844C41008148 @default.
- W4386207844 hasConceptScore W4386207844C41608201 @default.
- W4386207844 hasConceptScore W4386207844C52622490 @default.
- W4386207844 hasConceptScore W4386207844C66945725 @default.
- W4386207844 hasConceptScore W4386207844C71472368 @default.
- W4386207844 hasConceptScore W4386207844C80444323 @default.
- W4386207844 hasFunder F4320323085 @default.
- W4386207844 hasLocation W43862078441 @default.
- W4386207844 hasOpenAccess W4386207844 @default.
- W4386207844 hasPrimaryLocation W43862078441 @default.
- W4386207844 hasRelatedWork W2293457016 @default.
- W4386207844 hasRelatedWork W2398825887 @default.
- W4386207844 hasRelatedWork W2567035470 @default.
- W4386207844 hasRelatedWork W2789919619 @default.
- W4386207844 hasRelatedWork W2790173704 @default.
- W4386207844 hasRelatedWork W2887213206 @default.
- W4386207844 hasRelatedWork W2949267551 @default.
- W4386207844 hasRelatedWork W3094412894 @default.
- W4386207844 hasRelatedWork W3212410689 @default.
- W4386207844 hasRelatedWork W4287497346 @default.
- W4386207844 isParatext "false" @default.
- W4386207844 isRetracted "false" @default.
- W4386207844 workType "article" @default.