FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386408978> ?p ?o ?g. }

• W4386408978 endingPage "9919" @default.
• W4386408978 startingPage "9919" @default.
• W4386408978 abstract "Natural language understanding (NLU) is an important aspect of achieving human–machine interactions in the automotive application field, consisting of two core subtasks, multiple-intent detection, and slot filling (ID-SF). However, existing joint multiple ID-SF tasks in the Chinese automotive domain face two challenges: (1) There is a limited availability of Chinese multi-intent corpus data for research purposes in the automotive domain; (2) In the current models, the interaction between intent detection and slot filling is often unidirectional, which ultimately leads to inadequate accuracy in intent detection. A novel multi-intent parallel interactive framework based on heterogeneous graphs for the automotive applications field (Auto-HPIF) was proposed to overcome these issues. Its improvements mainly include three aspects: firstly, the incorporation of the Chinese bidirectional encoder representations from transformers (BERT) language model and Gaussian prior attention mechanism allow each word to acquire more comprehensive contextual information; secondly, the establishment of a heterogeneous graph parallel interactive network efficiently exploits intent and slot information, facilitating mutual guidance; lastly, the application of the cross-entropy loss function to the multi-intent classification task enhances the model’s robustness and adaptability. Additionally, a Chinese automotive multi-intent dataset (CADS) comprising 13,100 Chinese utterances, seven types of slots, and thirty types of intents were collected and annotated. The proposed framework model demonstrates significant improvements across various datasets. On the Chinese automotive multi-intent dataset (CADS), the model achieves an overall accuracy of 87.94%, marking a notable 2.07% enhancement over the previous best baseline. Additionally, the model performs commendably on two publicly available datasets. Specifically, it showcases a 3.0% increase in overall accuracy on the MixATIS dataset and a 0.7% improvement on the MixSNIPS dataset. These findings showcase the efficacy and generalizability of the proposed model in tackling the complexity of joint multiple ID-SF tasks within the Chinese automotive domain." @default.
• W4386408978 created "2023-09-05" @default.
• W4386408978 creator A5057942346 @default.
• W4386408978 creator A5065072240 @default.
• W4386408978 creator A5066683539 @default.
• W4386408978 creator A5081894037 @default.
• W4386408978 date "2023-09-01" @default.
• W4386408978 modified "2023-10-01" @default.
• W4386408978 title "Multi-Intent Natural Language Understanding Framework for Automotive Applications: A Heterogeneous Parallel Approach" @default.
• W4386408978 cites W2010152689 @default.
• W4386408978 cites W2077302143 @default.
• W4386408978 cites W2400801499 @default.
• W4386408978 cites W2789424053 @default.
• W4386408978 cites W2798968609 @default.
• W4386408978 cites W2803392141 @default.
• W4386408978 cites W2804945011 @default.
• W4386408978 cites W2946085385 @default.
• W4386408978 cites W2962739339 @default.
• W4386408978 cites W2963974889 @default.
• W4386408978 cites W2971167298 @default.
• W4386408978 cites W3013860672 @default.
• W4386408978 cites W3099757670 @default.
• W4386408978 cites W3158773425 @default.
• W4386408978 cites W3173794693 @default.
• W4386408978 cites W3193282380 @default.
• W4386408978 cites W3194303810 @default.
• W4386408978 cites W3194955531 @default.
• W4386408978 cites W4220884378 @default.
• W4386408978 cites W4221154429 @default.
• W4386408978 cites W4295088039 @default.
• W4386408978 cites W4323314822 @default.
• W4386408978 cites W4323856429 @default.
• W4386408978 cites W4327546846 @default.
• W4386408978 cites W4385573163 @default.
• W4386408978 doi "https://doi.org/10.3390/app13179919" @default.
• W4386408978 hasPublicationYear "2023" @default.
• W4386408978 type Work @default.
• W4386408978 citedByCount "0" @default.
• W4386408978 crossrefType "journal-article" @default.
• W4386408978 hasAuthorship W4386408978A5057942346 @default.
• W4386408978 hasAuthorship W4386408978A5065072240 @default.
• W4386408978 hasAuthorship W4386408978A5066683539 @default.
• W4386408978 hasAuthorship W4386408978A5081894037 @default.
• W4386408978 hasBestOaLocation W43864089781 @default.
• W4386408978 hasConcept C111919701 @default.
• W4386408978 hasConcept C118505674 @default.
• W4386408978 hasConcept C127413603 @default.
• W4386408978 hasConcept C146978453 @default.
• W4386408978 hasConcept C154945302 @default.
• W4386408978 hasConcept C165696696 @default.
• W4386408978 hasConcept C177606310 @default.
• W4386408978 hasConcept C18903297 @default.
• W4386408978 hasConcept C195324797 @default.
• W4386408978 hasConcept C2779439875 @default.
• W4386408978 hasConcept C38652104 @default.
• W4386408978 hasConcept C41008148 @default.
• W4386408978 hasConcept C526921623 @default.
• W4386408978 hasConcept C86803240 @default.
• W4386408978 hasConceptScore W4386408978C111919701 @default.
• W4386408978 hasConceptScore W4386408978C118505674 @default.
• W4386408978 hasConceptScore W4386408978C127413603 @default.
• W4386408978 hasConceptScore W4386408978C146978453 @default.
• W4386408978 hasConceptScore W4386408978C154945302 @default.
• W4386408978 hasConceptScore W4386408978C165696696 @default.
• W4386408978 hasConceptScore W4386408978C177606310 @default.
• W4386408978 hasConceptScore W4386408978C18903297 @default.
• W4386408978 hasConceptScore W4386408978C195324797 @default.
• W4386408978 hasConceptScore W4386408978C2779439875 @default.
• W4386408978 hasConceptScore W4386408978C38652104 @default.
• W4386408978 hasConceptScore W4386408978C41008148 @default.
• W4386408978 hasConceptScore W4386408978C526921623 @default.
• W4386408978 hasConceptScore W4386408978C86803240 @default.
• W4386408978 hasIssue "17" @default.
• W4386408978 hasLocation W43864089781 @default.
• W4386408978 hasOpenAccess W4386408978 @default.
• W4386408978 hasPrimaryLocation W43864089781 @default.
• W4386408978 hasRelatedWork W1542956019 @default.
• W4386408978 hasRelatedWork W1557745144 @default.
• W4386408978 hasRelatedWork W1599620240 @default.
• W4386408978 hasRelatedWork W2275988210 @default.
• W4386408978 hasRelatedWork W2331043530 @default.
• W4386408978 hasRelatedWork W2393933887 @default.
• W4386408978 hasRelatedWork W2886693075 @default.
• W4386408978 hasRelatedWork W2977842567 @default.
• W4386408978 hasRelatedWork W2997512100 @default.
• W4386408978 hasRelatedWork W3118511871 @default.
• W4386408978 hasVolume "13" @default.
• W4386408978 isParatext "false" @default.
• W4386408978 isRetracted "false" @default.
• W4386408978 workType "article" @default.