Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089741726> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3089741726 abstract "The task of Knowledge Base Question Answering (KBQA) is to provide a convenient way for the human to more efficiently and easily answer natural language questions using the substantial and valuable knowledge in the KB. Predicate generation is the most important sub-task of KBQA, which aims to generate the predicate paths from head entity to tail entity. Existing models mostly employ a seq2seq method to handle this task. However, the seq2seq method essentially is a classification model, which needs to know the number of the categories in advance. Meanwhile, KBs often are incompleteness and questions are always unbounded, which would cause the problem that the predicates of the questions would be beyond predefined categories. Obviously, the seq2seq model cannot handle this problem. In this paper, to solve the problem above, we explore to build an scoring module with strong genelization to score the predicates not in predefined categories, and also to improve the performance of the seq2seq method. To bridge the gap, we carefully design a reasoning module to score the predicates through reasonably employing the attention mechanism with memory ability. Simultaneously, in order to improve the generalization of the reasoning module, we try to use multi-task learning to enrich the represent of the reasoning module based on the idea of transfer learning. Massive experiments are conducted on two popular benchmark datasets - SimpleQuestion(SimQ) and WebQuestion(WebQ). The experimental results demonstrate that the proposed relation reasoning framework outperforms the state-of-the-art methods." @default.
- W3089741726 created "2020-10-08" @default.
- W3089741726 creator A5002911868 @default.
- W3089741726 creator A5054877470 @default.
- W3089741726 creator A5071759737 @default.
- W3089741726 date "2020-07-01" @default.
- W3089741726 modified "2023-10-16" @default.
- W3089741726 title "Enhancing Question Answering over Knowledge Base Using Dynamical Relation Reasoning" @default.
- W3089741726 cites W102708294 @default.
- W3089741726 cites W1801721664 @default.
- W3089741726 cites W1894439495 @default.
- W3089741726 cites W2094728533 @default.
- W3089741726 cites W2148721079 @default.
- W3089741726 cites W2184957013 @default.
- W3089741726 cites W2250539671 @default.
- W3089741726 cites W2251079237 @default.
- W3089741726 cites W2252231772 @default.
- W3089741726 cites W2471900581 @default.
- W3089741726 cites W2739716023 @default.
- W3089741726 cites W2891420675 @default.
- W3089741726 cites W2907356757 @default.
- W3089741726 cites W2929198159 @default.
- W3089741726 cites W2963608065 @default.
- W3089741726 cites W2963655104 @default.
- W3089741726 cites W2963738886 @default.
- W3089741726 doi "https://doi.org/10.1109/ijcnn48605.2020.9207428" @default.
- W3089741726 hasPublicationYear "2020" @default.
- W3089741726 type Work @default.
- W3089741726 sameAs 3089741726 @default.
- W3089741726 citedByCount "3" @default.
- W3089741726 countsByYear W30897417262022 @default.
- W3089741726 countsByYear W30897417262023 @default.
- W3089741726 crossrefType "proceedings-article" @default.
- W3089741726 hasAuthorship W3089741726A5002911868 @default.
- W3089741726 hasAuthorship W3089741726A5054877470 @default.
- W3089741726 hasAuthorship W3089741726A5071759737 @default.
- W3089741726 hasConcept C100776233 @default.
- W3089741726 hasConcept C124101348 @default.
- W3089741726 hasConcept C126322002 @default.
- W3089741726 hasConcept C13280743 @default.
- W3089741726 hasConcept C134306372 @default.
- W3089741726 hasConcept C140146324 @default.
- W3089741726 hasConcept C154945302 @default.
- W3089741726 hasConcept C162324750 @default.
- W3089741726 hasConcept C177148314 @default.
- W3089741726 hasConcept C185798385 @default.
- W3089741726 hasConcept C187736073 @default.
- W3089741726 hasConcept C199360897 @default.
- W3089741726 hasConcept C204321447 @default.
- W3089741726 hasConcept C205649164 @default.
- W3089741726 hasConcept C25343380 @default.
- W3089741726 hasConcept C2780451532 @default.
- W3089741726 hasConcept C33923547 @default.
- W3089741726 hasConcept C41008148 @default.
- W3089741726 hasConcept C44291984 @default.
- W3089741726 hasConcept C4554734 @default.
- W3089741726 hasConcept C71924100 @default.
- W3089741726 hasConceptScore W3089741726C100776233 @default.
- W3089741726 hasConceptScore W3089741726C124101348 @default.
- W3089741726 hasConceptScore W3089741726C126322002 @default.
- W3089741726 hasConceptScore W3089741726C13280743 @default.
- W3089741726 hasConceptScore W3089741726C134306372 @default.
- W3089741726 hasConceptScore W3089741726C140146324 @default.
- W3089741726 hasConceptScore W3089741726C154945302 @default.
- W3089741726 hasConceptScore W3089741726C162324750 @default.
- W3089741726 hasConceptScore W3089741726C177148314 @default.
- W3089741726 hasConceptScore W3089741726C185798385 @default.
- W3089741726 hasConceptScore W3089741726C187736073 @default.
- W3089741726 hasConceptScore W3089741726C199360897 @default.
- W3089741726 hasConceptScore W3089741726C204321447 @default.
- W3089741726 hasConceptScore W3089741726C205649164 @default.
- W3089741726 hasConceptScore W3089741726C25343380 @default.
- W3089741726 hasConceptScore W3089741726C2780451532 @default.
- W3089741726 hasConceptScore W3089741726C33923547 @default.
- W3089741726 hasConceptScore W3089741726C41008148 @default.
- W3089741726 hasConceptScore W3089741726C44291984 @default.
- W3089741726 hasConceptScore W3089741726C4554734 @default.
- W3089741726 hasConceptScore W3089741726C71924100 @default.
- W3089741726 hasLocation W30897417261 @default.
- W3089741726 hasOpenAccess W3089741726 @default.
- W3089741726 hasPrimaryLocation W30897417261 @default.
- W3089741726 hasRelatedWork W207304934 @default.
- W3089741726 hasRelatedWork W2609569121 @default.
- W3089741726 hasRelatedWork W2798237655 @default.
- W3089741726 hasRelatedWork W2951622387 @default.
- W3089741726 hasRelatedWork W2963655104 @default.
- W3089741726 hasRelatedWork W2970044932 @default.
- W3089741726 hasRelatedWork W4211238987 @default.
- W3089741726 hasRelatedWork W4319332036 @default.
- W3089741726 hasRelatedWork W4377703168 @default.
- W3089741726 hasRelatedWork W4379280886 @default.
- W3089741726 isParatext "false" @default.
- W3089741726 isRetracted "false" @default.
- W3089741726 magId "3089741726" @default.
- W3089741726 workType "article" @default.