Matches in SemOpenAlex for { <https://semopenalex.org/work/W143901095> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W143901095 endingPage "150" @default.
- W143901095 startingPage "141" @default.
- W143901095 abstract "Knowledge bases are useful resource for many applications, but reasoning new relationships between new entities based on them is difficult because they often lack the knowledge of new relations and entities. In this paper, we introduce the novel Neural Tensor Network (NTN)[1] model to reason new facts based on Chinese knowledge bases. We represent entities as an average of their constituting word or character vectors, which share the statistical strength between entities, such as . The NTN model uses a tensor network to replace a standard neural layer, which strengthen the interaction of two entity vectors in a simple and efficient way. In experiments, we compare the NTN and several other models, the results show that all models’ performance can be improved when word vectors are pre-trained from an unsupervised large corpora and character vectors don’t have this advantage. The NTN model outperforms others and reachs high classification accuracy 91.1% and 89.6% when using pre-trained word vectors and random character vectors, respectively. Therefore, when Chinese word segmentation is a difficult task, initialization with random character vectors is a feasible choice." @default.
- W143901095 created "2016-06-24" @default.
- W143901095 creator A5024215680 @default.
- W143901095 creator A5055393039 @default.
- W143901095 creator A5070659482 @default.
- W143901095 creator A5072019828 @default.
- W143901095 date "2014-01-01" @default.
- W143901095 modified "2023-09-26" @default.
- W143901095 title "Reasoning Over Relations Based on Chinese Knowledge Bases" @default.
- W143901095 cites W1550602550 @default.
- W143901095 cites W1992178984 @default.
- W143901095 cites W2152175008 @default.
- W143901095 cites W2247119764 @default.
- W143901095 cites W340632675 @default.
- W143901095 doi "https://doi.org/10.1007/978-3-319-12277-9_13" @default.
- W143901095 hasPublicationYear "2014" @default.
- W143901095 type Work @default.
- W143901095 sameAs 143901095 @default.
- W143901095 citedByCount "1" @default.
- W143901095 countsByYear W1439010952017 @default.
- W143901095 crossrefType "book-chapter" @default.
- W143901095 hasAuthorship W143901095A5024215680 @default.
- W143901095 hasAuthorship W143901095A5055393039 @default.
- W143901095 hasAuthorship W143901095A5070659482 @default.
- W143901095 hasAuthorship W143901095A5072019828 @default.
- W143901095 hasConcept C114466953 @default.
- W143901095 hasConcept C119857082 @default.
- W143901095 hasConcept C154945302 @default.
- W143901095 hasConcept C155281189 @default.
- W143901095 hasConcept C199360897 @default.
- W143901095 hasConcept C202444582 @default.
- W143901095 hasConcept C204321447 @default.
- W143901095 hasConcept C2524010 @default.
- W143901095 hasConcept C2780861071 @default.
- W143901095 hasConcept C33923547 @default.
- W143901095 hasConcept C41008148 @default.
- W143901095 hasConcept C50644808 @default.
- W143901095 hasConcept C90805587 @default.
- W143901095 hasConceptScore W143901095C114466953 @default.
- W143901095 hasConceptScore W143901095C119857082 @default.
- W143901095 hasConceptScore W143901095C154945302 @default.
- W143901095 hasConceptScore W143901095C155281189 @default.
- W143901095 hasConceptScore W143901095C199360897 @default.
- W143901095 hasConceptScore W143901095C202444582 @default.
- W143901095 hasConceptScore W143901095C204321447 @default.
- W143901095 hasConceptScore W143901095C2524010 @default.
- W143901095 hasConceptScore W143901095C2780861071 @default.
- W143901095 hasConceptScore W143901095C33923547 @default.
- W143901095 hasConceptScore W143901095C41008148 @default.
- W143901095 hasConceptScore W143901095C50644808 @default.
- W143901095 hasConceptScore W143901095C90805587 @default.
- W143901095 hasLocation W1439010951 @default.
- W143901095 hasOpenAccess W143901095 @default.
- W143901095 hasPrimaryLocation W1439010951 @default.
- W143901095 hasRelatedWork W2063925051 @default.
- W143901095 hasRelatedWork W2354222305 @default.
- W143901095 hasRelatedWork W2363407155 @default.
- W143901095 hasRelatedWork W2804608824 @default.
- W143901095 hasRelatedWork W2806021948 @default.
- W143901095 hasRelatedWork W2890522487 @default.
- W143901095 hasRelatedWork W2991463832 @default.
- W143901095 hasRelatedWork W3017774323 @default.
- W143901095 hasRelatedWork W77769009 @default.
- W143901095 hasRelatedWork W1629725936 @default.
- W143901095 isParatext "false" @default.
- W143901095 isRetracted "false" @default.
- W143901095 magId "143901095" @default.
- W143901095 workType "book-chapter" @default.