Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045133> ?p ?o ?g. }
- W4288045133 endingPage "100737" @default.
- W4288045133 startingPage "100737" @default.
- W4288045133 abstract "Aggregate question answering essentially returns answers for given questions by obtaining query graphs with unique dependencies between values and corresponding objects. Word order dependency, as the key to uniquely identify dependency of the query graph, reflects the dependencies between the words in the question. However, due to the semantic gap caused by the expression difference between questions encoded with word vectors and query graphs represented with logical formal elements, it is not trivial to match the correct query graph for the question. Most existing approaches design more expressive query graphs for complex questions and rank them just by directly calculating their similarities, ignoring the semantic gap between them. In this paper, we propose a novel Structure-sensitive Semantic Matching(SSM) approach that learns aligned representations of dependencies in questions and query graphs to eliminate their gap. First, we propose a cross-structure matching module to bridge the gap between two modalities(i.e., textual question and query graph). Then, we propose an entropy-based gated AQG filter to remove the structural noise caused by the uncertainty of dependencies. Finally, we present a two-channel query graph representation that fuses the semantics of abstract structure and grounding content of the query graph explicitly. Experimental results show that SSM could learn aligned representations of questions and query graphs to eliminate the gaps between their dependencies, and improves up to 12% (F1 score) on aggregation questions of two benchmark datasets." @default.
- W4288045133 created "2022-07-27" @default.
- W4288045133 creator A5001714538 @default.
- W4288045133 creator A5021162098 @default.
- W4288045133 creator A5030524599 @default.
- W4288045133 creator A5041328957 @default.
- W4288045133 creator A5080540494 @default.
- W4288045133 creator A5083304328 @default.
- W4288045133 creator A5084677096 @default.
- W4288045133 creator A5089611409 @default.
- W4288045133 date "2022-10-01" @default.
- W4288045133 modified "2023-09-28" @default.
- W4288045133 title "Structure-sensitive semantic matching for aggregate question answering over knowledge base" @default.
- W4288045133 cites W102708294 @default.
- W4288045133 cites W1894439495 @default.
- W4288045133 cites W1981419611 @default.
- W4288045133 cites W2019971182 @default.
- W4288045133 cites W2047237057 @default.
- W4288045133 cites W2079735306 @default.
- W4288045133 cites W2094728533 @default.
- W4288045133 cites W2126170172 @default.
- W4288045133 cites W2148721079 @default.
- W4288045133 cites W2151149636 @default.
- W4288045133 cites W2167665328 @default.
- W4288045133 cites W2250225488 @default.
- W4288045133 cites W2251287417 @default.
- W4288045133 cites W2252231772 @default.
- W4288045133 cites W2471900581 @default.
- W4288045133 cites W2591368218 @default.
- W4288045133 cites W2739716023 @default.
- W4288045133 cites W2763039547 @default.
- W4288045133 cites W2788653116 @default.
- W4288045133 cites W2798749466 @default.
- W4288045133 cites W2888128175 @default.
- W4288045133 cites W2889276770 @default.
- W4288045133 cites W2890560945 @default.
- W4288045133 cites W2890961898 @default.
- W4288045133 cites W2891420675 @default.
- W4288045133 cites W2915836468 @default.
- W4288045133 cites W2929198159 @default.
- W4288045133 cites W2945844671 @default.
- W4288045133 cites W2963448850 @default.
- W4288045133 cites W2963655104 @default.
- W4288045133 cites W2963794306 @default.
- W4288045133 cites W2964120615 @default.
- W4288045133 cites W2966747703 @default.
- W4288045133 cites W2970293467 @default.
- W4288045133 cites W2972551450 @default.
- W4288045133 cites W2980737818 @default.
- W4288045133 cites W2983745280 @default.
- W4288045133 cites W2997525715 @default.
- W4288045133 cites W2997937415 @default.
- W4288045133 cites W3003485993 @default.
- W4288045133 cites W3033893309 @default.
- W4288045133 cites W3034273250 @default.
- W4288045133 cites W3035272542 @default.
- W4288045133 cites W3116847845 @default.
- W4288045133 cites W3173625863 @default.
- W4288045133 cites W3190271517 @default.
- W4288045133 cites W3197277089 @default.
- W4288045133 cites W3211660723 @default.
- W4288045133 doi "https://doi.org/10.1016/j.websem.2022.100737" @default.
- W4288045133 hasPublicationYear "2022" @default.
- W4288045133 type Work @default.
- W4288045133 citedByCount "0" @default.
- W4288045133 crossrefType "journal-article" @default.
- W4288045133 hasAuthorship W4288045133A5001714538 @default.
- W4288045133 hasAuthorship W4288045133A5021162098 @default.
- W4288045133 hasAuthorship W4288045133A5030524599 @default.
- W4288045133 hasAuthorship W4288045133A5041328957 @default.
- W4288045133 hasAuthorship W4288045133A5080540494 @default.
- W4288045133 hasAuthorship W4288045133A5083304328 @default.
- W4288045133 hasAuthorship W4288045133A5084677096 @default.
- W4288045133 hasAuthorship W4288045133A5089611409 @default.
- W4288045133 hasConcept C115961682 @default.
- W4288045133 hasConcept C118689300 @default.
- W4288045133 hasConcept C132525143 @default.
- W4288045133 hasConcept C154945302 @default.
- W4288045133 hasConcept C164120249 @default.
- W4288045133 hasConcept C1667742 @default.
- W4288045133 hasConcept C192028432 @default.
- W4288045133 hasConcept C197657726 @default.
- W4288045133 hasConcept C23123220 @default.
- W4288045133 hasConcept C41008148 @default.
- W4288045133 hasConcept C80444323 @default.
- W4288045133 hasConcept C86034646 @default.
- W4288045133 hasConcept C97854310 @default.
- W4288045133 hasConcept C99016210 @default.
- W4288045133 hasConceptScore W4288045133C115961682 @default.
- W4288045133 hasConceptScore W4288045133C118689300 @default.
- W4288045133 hasConceptScore W4288045133C132525143 @default.
- W4288045133 hasConceptScore W4288045133C154945302 @default.
- W4288045133 hasConceptScore W4288045133C164120249 @default.
- W4288045133 hasConceptScore W4288045133C1667742 @default.
- W4288045133 hasConceptScore W4288045133C192028432 @default.
- W4288045133 hasConceptScore W4288045133C197657726 @default.
- W4288045133 hasConceptScore W4288045133C23123220 @default.
- W4288045133 hasConceptScore W4288045133C41008148 @default.