Extensible Chatbot Architecture Using Metamodels of Natural Language Understanding

Matić, Rade; Kabiljo, Miloš; Živković, Miodrag; Čabarkapa, Milan

doi:10.3390/electronics10182300

Cited by 34 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A chatbot platform must have the following three parts that really add conversational experience (Matic et al, 2021):…”

Section: Literature Reviewmentioning

confidence: 99%

“…The problem of flexibility and independence from only one NLU service (manufacturer) was solved using metamodels. (Matic et al, 2021) ADA uses NLU services such as RASA (RASA, 2016) and Dialogflow (Google Dialogflow, 2020) to understand user intentions. ADA analyses text and, based on machine learning techniques, compares and then generates intent and its entities.…”

Section: Chatbot Ada -Academic Digital Assistantmentioning

confidence: 99%

See 1 more Smart Citation

41 st International Conference on Organizational Science Development

2022

View full text Add to dashboard Cite

Povzetek Trajnostni razvoj je eden izmed ključnih dejavnikov razvoja v zadnjih tridesetih letih na gospodarskem, družbenem in okoljskem področju. V tej raziskavi smo se osredotočili na družbeni vidik trajnostnega razvoja, ki ga obravnava tudi četrti cilj: kakovostno izobraževanje v okviru Združenih narodov. Rezultati ankete pri 203 dijakih so pokazali, da imajo dijaki občutek nizkega znanja o trajnostnem razvoju, saj so se samoocenili s povprečno oceno 2,36 (od maks. 5) in s standardnim odklonom 0,72. Pri pomembnosti trajnostnega razvoja v družbi so dijaki ocenjevali boljše, povprečna ocena je bila 3,78, standardni odklon pa 0,80. Korelacijska analiza kaže na srednjo šibko povezanost med spremenljivkama ocene lastnega znanja in pomembnostjo trajnostnega razvoja. Definicija trajnostnega razvoja ni popolnoma razumljiva pri 48 % dijakov, saj na vprašanje niso odgovorili ali pa so odgovorili napačno. Četrtina (25 %) anketiranih dijakov razume trajnostni razvoj z vidika varovanja okolja, družbeni vidik so prepoznali v 7 %, ekonomski pa le v 2 %. Pri pridobivanju znanja na tem področju so v ospredju mediji in socialna omrežja.

show abstract

“…A chatbot platform must have the following three parts that really add conversational experience (Matic et al, 2021):…”

Section: Literature Reviewmentioning

confidence: 99%

Section: Chatbot Ada -Academic Digital Assistantmentioning

confidence: 99%

41 st International Conference on Organizational Science Development

2022

View full text Add to dashboard Cite

show abstract

“…Kabiljo et al [42] propose an ADA (Academic Digital Assistant) chatbot supported by natural language understanding to deal with the impact of COVID-19 [43] on the education system. Matic et al [44] thoroughly investigate the structure of common chatbots and introduced corresponding metamodels.…”

Section: Spoken Language Understandingmentioning

confidence: 99%

Learning High-Order Semantic Representation for Intent Classification and Slot Filling on Low-Resource Language via Hypergraph

Qi¹,

Gao²,

Wang³

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Representation of language is the rst and critical task for Natural Language Understanding (NLU) in a dialogue system. Pretraining, embedding model, and ne-tuning for intent classi cation and slot-lling are popular and well-performing approaches but are time consuming and ine cient for low-resource languages. Concretely, the out-of-vocabulary and transferring to di erent languages are two tough challenges for multilingual pretrained and cross-lingual transferring models. Furthermore, quality-proved parallel data are necessary for the current frameworks. Stepping over these challenges, di erent from the existing solutions, we propose a novel approach, the Hypergraph Transfer Encoding Network "HGTransEnNet. e proposed model leverages o -the-shelf high-quality pretrained word embedding models of resource-rich languages to learn the high-order semantic representation of low-resource languages in a transductive clustering manner of hypergraph modeling, which does not need parallel data. e experiments show that the representations learned by "HGTransEnNet" for low-resource language are more e ective than the state-of-the-art language models, which are pretrained on a large-scale multilingual or monolingual corpus, in intent classi cation and slot-lling tasks on Indonesian and English datasets.

show abstract

“…Chatbots are computer programs that simulate human-like conversations, and have become increasingly popular with advancements in natural language processing (NLP, a branch of Artificial Intelligence (AI) focusing on linguistic interactions between humans and computers). 8 Chatbots are used in a wide range of applications such as marketing and education, 9 and in health, including online medical consultation (Babylon Health), Florence the "personal nurse" reminding patients to take their medications, and diagnostic agents such as Ada Health, a virtual symptom checker. 10 Chatbots can be based on a number of theoretical foundations.…”

Section: Introductionmentioning

confidence: 99%

ChatGPT for Clinical Vignette Generation, Revision, and Evaluation

Benoit

2023

Preprint

View full text Add to dashboard Cite

Objective To determine the capabilities of ChatGPT for rapidly generating, rewriting, and evaluating (via diagnostic and triage accuracy) sets of clinical vignettes. Design We explored the capabilities of ChatGPT for generating and rewriting vignettes. First, we gave it natural language prompts to generate 10 new sets of 10 vignettes, each set for a different common childhood illness. Next, we had it generate 10 sets of 10 vignettes given a set of symptoms from which to draw. We then had it rewrite 15 existing pediatric vignettes at different levels of health literacy. Fourth, we asked it to generate 10 vignettes written as a parent, and rewrite these vignettes as a physician, then at a grade 8 reading level, before rewriting them from the original parent's perspective. Finally, we evaluated ChatGPT for diagnosis and triage for 45 clinical vignettes previously used for evaluating symptom checkers. Setting and participants ChatGPT, a publicly available, free chatbot. Main outcome measures Our main outcomes for de novo vignette generation were whether ChatGPT followed vignette creation instructions consistently, correctly, and listed reasonable symptoms for the disease being described. For generating vignettes from pre-existing symptom sets, we examined whether the symptom sets were used without introducing extra symptoms. Our main outcome for rewriting existing standardized vignettes to match patient demographics, and rewriting vignettes between styles, was whether symptoms were dropped or added outside the original vignette. Finally, our main outcomes examining diagnostic and triage accuracy on 45 standardized patient vignettes were whether the correct diagnosis was listed first, and if the correct triage recommendation was made. Results ChatGPT was able to quickly produce varied contexts and symptom profiles when writing vignettes based on an illness name, but overused some core disease symptoms. It was able to use given symptom lists as the basis for vignettes consistently, adding one additional (though appropriate) symptom from outside the list for one disease. Pediatric vignettes rewritten at different levels of health literacy showed more complex symptoms being dropped when writing at low health literacy in 87.5% of cases. While writing at high health literacy, it added a diagnosis to 80% of vignettes (91.7% correctly diagnosed). Symptoms were retained in 90% of cases when rewriting vignettes between viewpoints. When presented with 45 vignettes, ChatGPT identified illnesses with 75.6% (95% CI, 62.6% to 88.5%) first-pass diagnostic accuracy and 57.8% (95% CI, 42.9% to 72.7%) triage accuracy. Its use does require monitoring and has caveats, which we discuss. Conclusions ChatGPT was capable, with caveats and appropriate review, of generating, rewriting, and evaluating clinical vignettes.

show abstract

Extensible Chatbot Architecture Using Metamodels of Natural Language Understanding

Cited by 34 publications

References 31 publications

41 st International Conference on Organizational Science Development

41 st International Conference on Organizational Science Development

Learning High-Order Semantic Representation for Intent Classification and Slot Filling on Low-Resource Language via Hypergraph

ChatGPT for Clinical Vignette Generation, Revision, and Evaluation

Contact Info

Product

Resources

About