FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376876984> ?p ?o ?g. }

• W4376876984 endingPage "2886" @default.
• W4376876984 startingPage "2855" @default.
• W4376876984 abstract "Large-scale pre-trained language models (PLMs) such as BERT have recently achieved great success and become a milestone in natural language processing (NLP). It is now the consensus of the NLP community to adopt PLMs as the backbone for downstream tasks. In recent works on knowledge graph question answering (KGQA), BERT or its variants have become necessary in their KGQA models. However, there is still a lack of comprehensive research and comparison of the performance of different PLMs in KGQA. To this end, we summarize two basic KGQA frameworks based on PLMs without additional neural network modules to compare the performance of nine PLMs in terms of accuracy and efficiency. In addition, we present three benchmarks for larger-scale KGs based on the popular SimpleQuestions benchmark to investigate the scalability of PLMs. We carefully analyze the results of all PLMs-based KGQA basic frameworks on these benchmarks and two other popular datasets, WebQuestionSP and FreebaseQA, and find that knowledge distillation techniques and knowledge enhancement methods in PLMs are promising for KGQA. Furthermore, we test ChatGPT ( https://chat.openai.com/ ), which has drawn a great deal of attention in the NLP community, demonstrating its impressive capabilities and limitations in zero-shot KGQA. We have released the code and benchmarks to promote the use of PLMs on KGQA ( https://github.com/aannonymouuss/PLMs-in-Practical-KBQA )." @default.
• W4376876984 created "2023-05-18" @default.
• W4376876984 creator A5012727381 @default.
• W4376876984 creator A5022377161 @default.
• W4376876984 creator A5032038161 @default.
• W4376876984 creator A5034606659 @default.
• W4376876984 creator A5050830339 @default.
• W4376876984 creator A5066422711 @default.
• W4376876984 creator A5085691361 @default.
• W4376876984 date "2023-05-17" @default.
• W4376876984 modified "2023-10-18" @default.
• W4376876984 title "An empirical study of pre-trained language models in simple knowledge graph question answering" @default.
• W4376876984 cites W2064675550 @default.
• W4376876984 cites W2094728533 @default.
• W4376876984 cites W2250539671 @default.
• W4376876984 cites W2511149293 @default.
• W4376876984 cites W2605089588 @default.
• W4376876984 cites W2618530766 @default.
• W4376876984 cites W2739716023 @default.
• W4376876984 cites W2759281352 @default.
• W4376876984 cites W2908230750 @default.
• W4376876984 cites W2953356739 @default.
• W4376876984 cites W2955202831 @default.
• W4376876984 cites W2962745909 @default.
• W4376876984 cites W2963341956 @default.
• W4376876984 cites W2963655104 @default.
• W4376876984 cites W2963682631 @default.
• W4376876984 cites W2963738886 @default.
• W4376876984 cites W2963897632 @default.
• W4376876984 cites W2970641574 @default.
• W4376876984 cites W2970986510 @default.
• W4376876984 cites W2981039167 @default.
• W4376876984 cites W2997110185 @default.
• W4376876984 cites W3011574394 @default.
• W4376876984 cites W3034273250 @default.
• W4376876984 cites W3091091747 @default.
• W4376876984 cites W3098862418 @default.
• W4376876984 cites W3104415840 @default.
• W4376876984 cites W3104616515 @default.
• W4376876984 cites W3104748221 @default.
• W4376876984 cites W3105966348 @default.
• W4376876984 cites W3115280218 @default.
• W4376876984 cites W3144724153 @default.
• W4376876984 cites W3151929433 @default.
• W4376876984 cites W3152740956 @default.
• W4376876984 cites W3156366114 @default.
• W4376876984 cites W3175795662 @default.
• W4376876984 cites W3196758600 @default.
• W4376876984 cites W3199258975 @default.
• W4376876984 cites W3204877056 @default.
• W4376876984 cites W3211660723 @default.
• W4376876984 cites W3217374296 @default.
• W4376876984 cites W4200072846 @default.
• W4376876984 cites W4225580830 @default.
• W4376876984 cites W4226148660 @default.
• W4376876984 cites W4226510082 @default.
• W4376876984 cites W4385572953 @default.
• W4376876984 doi "https://doi.org/10.1007/s11280-023-01166-y" @default.
• W4376876984 hasPublicationYear "2023" @default.
• W4376876984 type Work @default.
• W4376876984 citedByCount "0" @default.
• W4376876984 crossrefType "journal-article" @default.
• W4376876984 hasAuthorship W4376876984A5012727381 @default.
• W4376876984 hasAuthorship W4376876984A5022377161 @default.
• W4376876984 hasAuthorship W4376876984A5032038161 @default.
• W4376876984 hasAuthorship W4376876984A5034606659 @default.
• W4376876984 hasAuthorship W4376876984A5050830339 @default.
• W4376876984 hasAuthorship W4376876984A5066422711 @default.
• W4376876984 hasAuthorship W4376876984A5085691361 @default.
• W4376876984 hasBestOaLocation W43768769842 @default.
• W4376876984 hasConcept C119857082 @default.
• W4376876984 hasConcept C132525143 @default.
• W4376876984 hasConcept C13280743 @default.
• W4376876984 hasConcept C137293760 @default.
• W4376876984 hasConcept C154945302 @default.
• W4376876984 hasConcept C185798385 @default.
• W4376876984 hasConcept C204321447 @default.
• W4376876984 hasConcept C205649164 @default.
• W4376876984 hasConcept C2987255567 @default.
• W4376876984 hasConcept C41008148 @default.
• W4376876984 hasConcept C44291984 @default.
• W4376876984 hasConcept C48044578 @default.
• W4376876984 hasConcept C77088390 @default.
• W4376876984 hasConcept C80444323 @default.
• W4376876984 hasConceptScore W4376876984C119857082 @default.
• W4376876984 hasConceptScore W4376876984C132525143 @default.
• W4376876984 hasConceptScore W4376876984C13280743 @default.
• W4376876984 hasConceptScore W4376876984C137293760 @default.
• W4376876984 hasConceptScore W4376876984C154945302 @default.
• W4376876984 hasConceptScore W4376876984C185798385 @default.
• W4376876984 hasConceptScore W4376876984C204321447 @default.
• W4376876984 hasConceptScore W4376876984C205649164 @default.
• W4376876984 hasConceptScore W4376876984C2987255567 @default.
• W4376876984 hasConceptScore W4376876984C41008148 @default.
• W4376876984 hasConceptScore W4376876984C44291984 @default.
• W4376876984 hasConceptScore W4376876984C48044578 @default.
• W4376876984 hasConceptScore W4376876984C77088390 @default.
• W4376876984 hasConceptScore W4376876984C80444323 @default.

• next