FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285222754> ?p ?o ?g. }

• W4285222754 endingPage "50478" @default.
• W4285222754 startingPage "50467" @default.
• W4285222754 abstract "Most Knowledge Graph-based Question Answering (KGQA) systems rely on training data to reach their optimal performance. However, acquiring training data for supervised systems is both time-consuming and resource-intensive. To address this, in this paper, we propose <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Tree-KGQA</b> , an unsupervised KGQA system leveraging pre-trained language models and tree-based algorithms. Entity and relation linking are essential components of any KGQA system. We employ several pre-trained language models in the entity linking task to recognize the entities mentioned in the question and obtain the contextual representation for indexing. Furthermore, for relation linking we incorporate a pre-trained language model previously trained for language inference task. Finally, we introduce a novel algorithm for extracting the answer entities from a KG, where we construct a forest of interpretations and introduce tree-walking and tree disambiguation techniques. Our algorithm uses the linked relation and predicts the tree branches that eventually lead to the potential answer entities. The proposed method achieves 4.5% and 7.1% gains in F1 score in entity linking tasks on LC-QuAD 2.0 and LC-QuAD 2.0 (KBpearl) datasets, respectively, and a 5.4% increase in the relation linking task on LC-QuAD 2.0 (KBpearl). The comprehensive evaluations demonstrate that our unsupervised KGQA approach outperforms other supervised state-of-the-art methods on the WebQSP-WD test set (1.4% increase in F1 score) - without training on the target dataset." @default.
• W4285222754 created "2022-07-14" @default.
• W4285222754 creator A5039437456 @default.
• W4285222754 creator A5067133778 @default.
• W4285222754 creator A5069462779 @default.
• W4285222754 creator A5082639253 @default.
• W4285222754 date "2022-01-01" @default.
• W4285222754 modified "2023-10-02" @default.
• W4285222754 title "Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs" @default.
• W4285222754 cites W1529731474 @default.
• W4285222754 cites W1552847225 @default.
• W4285222754 cites W2094728533 @default.
• W4285222754 cites W2104583100 @default.
• W4285222754 cites W2123142779 @default.
• W4285222754 cites W2251079237 @default.
• W4285222754 cites W2546950329 @default.
• W4285222754 cites W2765782497 @default.
• W4285222754 cites W2774249241 @default.
• W4285222754 cites W2807418422 @default.
• W4285222754 cites W2892094955 @default.
• W4285222754 cites W2908230750 @default.
• W4285222754 cites W2915836468 @default.
• W4285222754 cites W2943186426 @default.
• W4285222754 cites W2946606955 @default.
• W4285222754 cites W2952826391 @default.
• W4285222754 cites W2962881743 @default.
• W4285222754 cites W2963102202 @default.
• W4285222754 cites W2963448850 @default.
• W4285222754 cites W2963490187 @default.
• W4285222754 cites W2963897632 @default.
• W4285222754 cites W2964044040 @default.
• W4285222754 cites W2964167098 @default.
• W4285222754 cites W2970641574 @default.
• W4285222754 cites W2971155257 @default.
• W4285222754 cites W2980401255 @default.
• W4285222754 cites W2980737818 @default.
• W4285222754 cites W2988898811 @default.
• W4285222754 cites W2997028620 @default.
• W4285222754 cites W2998702515 @default.
• W4285222754 cites W3013778764 @default.
• W4285222754 cites W3016970897 @default.
• W4285222754 cites W3034273250 @default.
• W4285222754 cites W3034879633 @default.
• W4285222754 cites W3034999214 @default.
• W4285222754 cites W3035094063 @default.
• W4285222754 cites W3098862418 @default.
• W4285222754 cites W3101786835 @default.
• W4285222754 cites W3104616515 @default.
• W4285222754 cites W3104748221 @default.
• W4285222754 cites W3105124442 @default.
• W4285222754 cites W3106642367 @default.
• W4285222754 cites W3176119108 @default.
• W4285222754 cites W3201854766 @default.
• W4285222754 doi "https://doi.org/10.1109/access.2022.3173355" @default.
• W4285222754 hasPublicationYear "2022" @default.
• W4285222754 type Work @default.
• W4285222754 citedByCount "5" @default.
• W4285222754 countsByYear W42852227542022 @default.
• W4285222754 countsByYear W42852227542023 @default.
• W4285222754 crossrefType "journal-article" @default.
• W4285222754 hasAuthorship W4285222754A5039437456 @default.
• W4285222754 hasAuthorship W4285222754A5067133778 @default.
• W4285222754 hasAuthorship W4285222754A5069462779 @default.
• W4285222754 hasAuthorship W4285222754A5082639253 @default.
• W4285222754 hasBestOaLocation W42852227541 @default.
• W4285222754 hasConcept C113174947 @default.
• W4285222754 hasConcept C119857082 @default.
• W4285222754 hasConcept C124101348 @default.
• W4285222754 hasConcept C132525143 @default.
• W4285222754 hasConcept C134306372 @default.
• W4285222754 hasConcept C153604712 @default.
• W4285222754 hasConcept C154945302 @default.
• W4285222754 hasConcept C162324750 @default.
• W4285222754 hasConcept C177264268 @default.
• W4285222754 hasConcept C187736073 @default.
• W4285222754 hasConcept C199360897 @default.
• W4285222754 hasConcept C204321447 @default.
• W4285222754 hasConcept C25343380 @default.
• W4285222754 hasConcept C2776214188 @default.
• W4285222754 hasConcept C2780451532 @default.
• W4285222754 hasConcept C33923547 @default.
• W4285222754 hasConcept C41008148 @default.
• W4285222754 hasConcept C44291984 @default.
• W4285222754 hasConcept C75165309 @default.
• W4285222754 hasConcept C80444323 @default.
• W4285222754 hasConceptScore W4285222754C113174947 @default.
• W4285222754 hasConceptScore W4285222754C119857082 @default.
• W4285222754 hasConceptScore W4285222754C124101348 @default.
• W4285222754 hasConceptScore W4285222754C132525143 @default.
• W4285222754 hasConceptScore W4285222754C134306372 @default.
• W4285222754 hasConceptScore W4285222754C153604712 @default.
• W4285222754 hasConceptScore W4285222754C154945302 @default.
• W4285222754 hasConceptScore W4285222754C162324750 @default.
• W4285222754 hasConceptScore W4285222754C177264268 @default.
• W4285222754 hasConceptScore W4285222754C187736073 @default.
• W4285222754 hasConceptScore W4285222754C199360897 @default.
• W4285222754 hasConceptScore W4285222754C204321447 @default.
• W4285222754 hasConceptScore W4285222754C25343380 @default.

• next