FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225533634> ?p ?o ?g. }

• W4225533634 endingPage "5063" @default.
• W4225533634 startingPage "5051" @default.
• W4225533634 abstract "With the rapid growth of large-scale knowledge bases (KBs), knowledge base question answering (KBQA) has attracted increasing attention recently. Relation detection plays an important role in the KBQA system, which finds a compatible answer by analyzing the semantics of questions and querying and reasoning with multiple KB triples. Significant progress has been made by deep neural networks. However, existing methods often concern on detecting single-hop relation without path reasoning, and a few of these methods exploit the multihop relation reasoning, which involves the answer reasoning from the noisy and abundant relational paths in the KB. Meanwhile, the relatedness between question and answer candidates has received little attention and remains unsolved. This article proposes a novel knowledge-based reasoning network (KRN) for relation detection, including both single-hop relation and multihop relation. To address the semantic gap problem in question-answer interaction, we first learn attentive question representations according to the influence of answer aspects. Then, we learn the single-hop relation sequence through different levels of abstraction and adopt the KB entity and structure information to denoise the multihop relation detection task. Finally, we adopt a Siamese network to measure the similarity between question representation and relation representation for both single-hop and multihop relation KBQA tasks. We conduct experiments on two well-known benchmarks, SimpleQuestions and WebQSP, and the results show the superiority of our approach over the state-of-the-art models for both single-hop and multihop relation detection. Our model also achieves a significant improvement over existing methods on KBQA end task. Further analysis demonstrates the robustness and the applicability of the proposed approach." @default.
• W4225533634 created "2022-05-05" @default.
• W4225533634 creator A5005157362 @default.
• W4225533634 creator A5022672030 @default.
• W4225533634 creator A5046405692 @default.
• W4225533634 creator A5046576694 @default.
• W4225533634 creator A5070785308 @default.
• W4225533634 creator A5090695897 @default.
• W4225533634 date "2023-08-01" @default.
• W4225533634 modified "2023-09-25" @default.
• W4225533634 title "Knowledge-Based Reasoning Network for Relation Detection" @default.
• W4225533634 cites W2022166150 @default.
• W4225533634 cites W2029249040 @default.
• W4225533634 cites W2064675550 @default.
• W4225533634 cites W2081580037 @default.
• W4225533634 cites W2094728533 @default.
• W4225533634 cites W2107598941 @default.
• W4225533634 cites W2126170172 @default.
• W4225533634 cites W2147308966 @default.
• W4225533634 cites W2148721079 @default.
• W4225533634 cites W2150406842 @default.
• W4225533634 cites W2174945390 @default.
• W4225533634 cites W2250175451 @default.
• W4225533634 cites W2250225488 @default.
• W4225533634 cites W2251079237 @default.
• W4225533634 cites W2251287417 @default.
• W4225533634 cites W2309189658 @default.
• W4225533634 cites W2515462165 @default.
• W4225533634 cites W2558777232 @default.
• W4225533634 cites W2561148973 @default.
• W4225533634 cites W2579393094 @default.
• W4225533634 cites W2618230655 @default.
• W4225533634 cites W2743373436 @default.
• W4225533634 cites W2755637027 @default.
• W4225533634 cites W2759136286 @default.
• W4225533634 cites W2759281352 @default.
• W4225533634 cites W2798633885 @default.
• W4225533634 cites W2799201288 @default.
• W4225533634 cites W2804916561 @default.
• W4225533634 cites W2889344053 @default.
• W4225533634 cites W2891791019 @default.
• W4225533634 cites W2894980269 @default.
• W4225533634 cites W2902551236 @default.
• W4225533634 cites W2951682790 @default.
• W4225533634 cites W2953356739 @default.
• W4225533634 cites W2954048108 @default.
• W4225533634 cites W2962739339 @default.
• W4225533634 cites W2963655104 @default.
• W4225533634 cites W2963682631 @default.
• W4225533634 cites W2963738886 @default.
• W4225533634 cites W2980248933 @default.
• W4225533634 cites W2984147501 @default.
• W4225533634 cites W2998385486 @default.
• W4225533634 cites W3003507729 @default.
• W4225533634 cites W3035272542 @default.
• W4225533634 cites W303777527 @default.
• W4225533634 cites W3045725402 @default.
• W4225533634 cites W3084836829 @default.
• W4225533634 cites W3089741726 @default.
• W4225533634 cites W3115829589 @default.
• W4225533634 cites W3116847845 @default.
• W4225533634 cites W3117865619 @default.
• W4225533634 cites W3147172970 @default.
• W4225533634 cites W3156366114 @default.
• W4225533634 cites W4236640001 @default.
• W4225533634 cites W68132019 @default.
• W4225533634 cites W3034598693 @default.
• W4225533634 doi "https://doi.org/10.1109/tnnls.2021.3123751" @default.
• W4225533634 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34752410" @default.
• W4225533634 hasPublicationYear "2023" @default.
• W4225533634 type Work @default.
• W4225533634 citedByCount "2" @default.
• W4225533634 countsByYear W42255336342022 @default.
• W4225533634 crossrefType "journal-article" @default.
• W4225533634 hasAuthorship W4225533634A5005157362 @default.
• W4225533634 hasAuthorship W4225533634A5022672030 @default.
• W4225533634 hasAuthorship W4225533634A5046405692 @default.
• W4225533634 hasAuthorship W4225533634A5046576694 @default.
• W4225533634 hasAuthorship W4225533634A5070785308 @default.
• W4225533634 hasAuthorship W4225533634A5090695897 @default.
• W4225533634 hasBestOaLocation W42255336341 @default.
• W4225533634 hasConcept C103278499 @default.
• W4225533634 hasConcept C111472728 @default.
• W4225533634 hasConcept C115961682 @default.
• W4225533634 hasConcept C124101348 @default.
• W4225533634 hasConcept C124304363 @default.
• W4225533634 hasConcept C138885662 @default.
• W4225533634 hasConcept C154945302 @default.
• W4225533634 hasConcept C165696696 @default.
• W4225533634 hasConcept C17744445 @default.
• W4225533634 hasConcept C199539241 @default.
• W4225533634 hasConcept C25343380 @default.
• W4225533634 hasConcept C25906391 @default.
• W4225533634 hasConcept C2776359362 @default.
• W4225533634 hasConcept C31258907 @default.
• W4225533634 hasConcept C38652104 @default.
• W4225533634 hasConcept C41008148 @default.
• W4225533634 hasConcept C4554734 @default.

• next