Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386824983> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4386824983 endingPage "101513" @default.
- W4386824983 startingPage "101498" @default.
- W4386824983 abstract "Semantic sentence matching plays an essential role in resolving many problems in natural language processing (NLP) field, it has gained increasing research focus and shown great improvements in recent years. However, most currently existing researches are for English sentence matching, research on Chinese semantic matching are relatively less. Moreover, due to the rather complicated contextual expressions and grammatical structure of Chinese language, many existing models are still unable to quite effectively capture interaction information between sentences. Thus, in this work, we attempt to propose a novel deep model to better address Chinese semantic sentence matching. Specifically, the convolutional neural networks with various kernel sizes are first employed for the multi-granular contextual encoding of sentences, combined with multiple different cross-sentence alignment mechanisms, the semantic interactions can be more clearly and profoundly performed at various granularity combinations between sentences. Additionally, rather than serially stacking multiple interaction layers, we organize multiple interaction layers in a parallel manner, and by further introduction of attention pooling, the semantically aligned sentence attentive vectors would be adaptively aggregated from both perspectives of alignment mechanisms and granularity combinations, thus more stable and effective sentence interactive features can be extracted while attempting to alleviate potential sentence alignment error propagation issue existed in hierarchically stacked interaction structure. Finally, extensive experiments are conducted to evaluate the performance of our model, the experimental results demonstrate that our proposed approach outperforms many state-of-the-art models on sentence matching and is capable of gaining a more accurate understanding of semantic relationships between Chinese sentences." @default.
- W4386824983 created "2023-09-19" @default.
- W4386824983 creator A5018255912 @default.
- W4386824983 creator A5023271869 @default.
- W4386824983 date "2023-01-01" @default.
- W4386824983 modified "2023-09-27" @default.
- W4386824983 title "Semantic Sentence Matching based on Multiple Parallelly Organized Interaction Layers At Various Granularity Combinations with Two-stage Aggregation Strategy" @default.
- W4386824983 cites W1840435438 @default.
- W4386824983 cites W2048476252 @default.
- W4386824983 cites W2211192759 @default.
- W4386824983 cites W2250889812 @default.
- W4386824983 cites W2265289447 @default.
- W4386824983 cites W2286300105 @default.
- W4386824983 cites W2413794162 @default.
- W4386824983 cites W2491664569 @default.
- W4386824983 cites W2508865106 @default.
- W4386824983 cites W2593833795 @default.
- W4386824983 cites W2773143256 @default.
- W4386824983 cites W2900874631 @default.
- W4386824983 cites W2909646526 @default.
- W4386824983 cites W2915045583 @default.
- W4386824983 cites W2919057541 @default.
- W4386824983 cites W2953075226 @default.
- W4386824983 cites W2962739339 @default.
- W4386824983 cites W2963542836 @default.
- W4386824983 cites W2969068412 @default.
- W4386824983 cites W2972599464 @default.
- W4386824983 cites W2980346149 @default.
- W4386824983 cites W3003718262 @default.
- W4386824983 cites W3010763821 @default.
- W4386824983 cites W3012016325 @default.
- W4386824983 cites W3027134841 @default.
- W4386824983 cites W3119200132 @default.
- W4386824983 cites W3146366485 @default.
- W4386824983 cites W3166806411 @default.
- W4386824983 cites W3180251298 @default.
- W4386824983 cites W3184218698 @default.
- W4386824983 cites W3197287757 @default.
- W4386824983 cites W3200275576 @default.
- W4386824983 cites W4220863817 @default.
- W4386824983 cites W4282039125 @default.
- W4386824983 doi "https://doi.org/10.1109/access.2023.3315840" @default.
- W4386824983 hasPublicationYear "2023" @default.
- W4386824983 type Work @default.
- W4386824983 citedByCount "0" @default.
- W4386824983 crossrefType "journal-article" @default.
- W4386824983 hasAuthorship W4386824983A5018255912 @default.
- W4386824983 hasAuthorship W4386824983A5023271869 @default.
- W4386824983 hasBestOaLocation W43868249831 @default.
- W4386824983 hasConcept C105795698 @default.
- W4386824983 hasConcept C111919701 @default.
- W4386824983 hasConcept C120665830 @default.
- W4386824983 hasConcept C121332964 @default.
- W4386824983 hasConcept C154945302 @default.
- W4386824983 hasConcept C165064840 @default.
- W4386824983 hasConcept C177774035 @default.
- W4386824983 hasConcept C184337299 @default.
- W4386824983 hasConcept C192209626 @default.
- W4386824983 hasConcept C199360897 @default.
- W4386824983 hasConcept C204321447 @default.
- W4386824983 hasConcept C2777530160 @default.
- W4386824983 hasConcept C33923547 @default.
- W4386824983 hasConcept C41008148 @default.
- W4386824983 hasConcept C67277372 @default.
- W4386824983 hasConcept C70437156 @default.
- W4386824983 hasConceptScore W4386824983C105795698 @default.
- W4386824983 hasConceptScore W4386824983C111919701 @default.
- W4386824983 hasConceptScore W4386824983C120665830 @default.
- W4386824983 hasConceptScore W4386824983C121332964 @default.
- W4386824983 hasConceptScore W4386824983C154945302 @default.
- W4386824983 hasConceptScore W4386824983C165064840 @default.
- W4386824983 hasConceptScore W4386824983C177774035 @default.
- W4386824983 hasConceptScore W4386824983C184337299 @default.
- W4386824983 hasConceptScore W4386824983C192209626 @default.
- W4386824983 hasConceptScore W4386824983C199360897 @default.
- W4386824983 hasConceptScore W4386824983C204321447 @default.
- W4386824983 hasConceptScore W4386824983C2777530160 @default.
- W4386824983 hasConceptScore W4386824983C33923547 @default.
- W4386824983 hasConceptScore W4386824983C41008148 @default.
- W4386824983 hasConceptScore W4386824983C67277372 @default.
- W4386824983 hasConceptScore W4386824983C70437156 @default.
- W4386824983 hasLocation W43868249831 @default.
- W4386824983 hasOpenAccess W4386824983 @default.
- W4386824983 hasPrimaryLocation W43868249831 @default.
- W4386824983 hasRelatedWork W1122501095 @default.
- W4386824983 hasRelatedWork W1492132281 @default.
- W4386824983 hasRelatedWork W159132833 @default.
- W4386824983 hasRelatedWork W1971791118 @default.
- W4386824983 hasRelatedWork W2293457016 @default.
- W4386824983 hasRelatedWork W2379525370 @default.
- W4386824983 hasRelatedWork W2952345041 @default.
- W4386824983 hasRelatedWork W4379781268 @default.
- W4386824983 hasRelatedWork W87581401 @default.
- W4386824983 hasRelatedWork W2143593218 @default.
- W4386824983 hasVolume "11" @default.
- W4386824983 isParatext "false" @default.
- W4386824983 isRetracted "false" @default.
- W4386824983 workType "article" @default.