000117173 001__ 117173
000117173 005__ 20240319080959.0
000117173 0247_ $$2doi$$a10.3390/s22062364
000117173 0248_ $$2sideral$$a128627
000117173 037__ $$aART-2022-128627
000117173 041__ $$aeng
000117173 100__ $$0(orcid)0000-0003-2608-6431$$aRoca Mainer, S.$$uUniversidad de Zaragoza
000117173 245__ $$aA Study on the Impacts of Slot Types and Training Data on Joint Natural Language Understanding in a Spanish Medication Management Assistant Scenario
000117173 260__ $$c2022
000117173 5060_ $$aAccess copy available to the general public$$fUnrestricted
000117173 5203_ $$aThis study evaluates the impacts of slot tagging and training data length on joint natural language understanding (NLU) models for medication management scenarios using chatbots in Spanish. In this study, we define the intents (purposes of the sentences) for medication management scenarios and two types of slot tags. For training the model, we generated four datasets, combining long/short sentences with long/short slots, while for testing, we collect the data from real interactions of users with a chatbot. For the comparative analysis, we chose six joint NLU models (SlotRefine, stack-propagation framework, SF-ID network, capsule-NLU, slot-gated modeling, and a joint SLU-LM model) from the literature. The results show that the best performance (with a sentence-level semantic accuracy of 68.6%, an F1-score of 76.4% for slot filling, and an accuracy of 79.3% for intent detection) is achieved using short sentences and short slots. Our results suggest that joint NLU models trained with short slots yield better results than those trained with long slots for the slot filling task. The results also indicate that short slots could be a better choice for the dialog system because of their simplicity. Importantly, the work demonstrates that the performance of the joint NLU models can be improved by selecting the correct slot configuration according to the usage scenario. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
000117173 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FEDER/T31-20R$$9info:eu-repo/grantAgreement/ES/MINECO/BES-2017-082017$$9info:eu-repo/grantAgreement/ES/MINECO-FEDER/TIN2016-76770-R
000117173 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000117173 590__ $$a3.9$$b2022
000117173 592__ $$a0.764$$b2022
000117173 591__ $$aCHEMISTRY, ANALYTICAL$$b26 / 86 = 0.302$$c2022$$dQ2$$eT1
000117173 593__ $$aInstrumentation$$c2022$$dQ1
000117173 591__ $$aINSTRUMENTS & INSTRUMENTATION$$b19 / 63 = 0.302$$c2022$$dQ2$$eT1
000117173 593__ $$aAnalytical Chemistry$$c2022$$dQ1
000117173 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b100 / 274 = 0.365$$c2022$$dQ2$$eT2
000117173 593__ $$aMedicine (miscellaneous)$$c2022$$dQ2
000117173 593__ $$aInformation Systems$$c2022$$dQ2
000117173 593__ $$aBiochemistry$$c2022$$dQ2
000117173 593__ $$aAtomic and Molecular Physics, and Optics$$c2022$$dQ2
000117173 593__ $$aElectrical and Electronic Engineering$$c2022$$dQ2
000117173 594__ $$a6.8$$b2022
000117173 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000117173 700__ $$aRosset, S.
000117173 700__ $$0(orcid)0000-0001-9485-7678$$aGarcía Moros, J.$$uUniversidad de Zaragoza
000117173 700__ $$0(orcid)0000-0002-5254-1402$$aAlesanco Iglesias, Á.$$uUniversidad de Zaragoza
000117173 7102_ $$15008$$2560$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Ingeniería Telemática
000117173 773__ $$g22, 6 (2022), 2364 [13 pp]$$pSensors$$tSensors$$x1424-8220
000117173 8564_ $$s5602925$$uhttps://zaguan.unizar.es/record/117173/files/texto_completo.pdf$$yVersión publicada
000117173 8564_ $$s2674757$$uhttps://zaguan.unizar.es/record/117173/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000117173 909CO $$ooai:zaguan.unizar.es:117173$$particulos$$pdriver
000117173 951__ $$a2024-03-18-13:56:41
000117173 980__ $$aARTICLE