You need to build a chatbot that meets the following requirements:
✑ Supports chit-chat, knowledge base, and multilingual models
✑ Performs sentiment analysis on user messages
✑ Selects the best language model automatically
What should you integrate into the chatbot?
To meet the requirements of supporting chit-chat, knowledge base, multilingual models, performing sentiment analysis, and automatically selecting the best language model, the appropriate tools to integrate would be QnA Maker, Language Understanding (LUIS), and Dispatch. QnA Maker provides a robust knowledge base for answering questions, Language Understanding helps in understanding user intents and entities for natural language interaction, and Dispatch is crucial for managing and routing between multiple language models and other services. These combined tools address all the specified requirements comprehensively.
To build the chatbot, integrate: A. QnA Maker, Language Understanding, and Dispatch These tools together will support chit-chat, knowledge base queries, multilingual capabilities, sentiment analysis, and automatic selection of the best language model.
Language Understanding: An AI service that allows users to interact with your applications, bots, and IoT devices by using natural language. QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information. Text Analytics: Mine insights in unstructured text using natural language processing (NLP)"no machine learning expertise required. Gain a deeper understanding of customer opinions with sentiment analysis. The Language Detection feature of the Azure Text Analytics REST API evaluates text input. Dispatch uses sample utterances for each of your botג - so this is not required
C is right answer.
C is right.
As Luis is outdated (with its Dispatch option), I must be C
The correct answer is A. QnA Maker, Language Understanding, Dispatch. The reason is: QnA Maker: Knowledge Base Support. Answers frequently asked questions and allows interaction. Language understanding (LUIS): Understanding user intents and entities is essential for meaningful answers and message routing. Dispatch: To automatically choose the best language model from user input. It manages numerous language models and selects one for a query. Option B must be revised since translator and speech are unrelated to providing chit-chat, knowledge bases, multilingual models, sentiment analysis, and automatic language model selection. The criteria already cover sentiment analysis; hence, Option C is inappropriate. Text analytics is mainly used to derive insights from text data. QnA Maker supports knowledge bases better than text analytics. Option D must be corrected because text analytics is unrelated to the criteria, and the translator prioritises translation over language model selection.
I think the answer option is A (see https://learn.microsoft.com/en-us/azure/ai-services/qnamaker/choose-natural-language-processing-service)
Took the exam on 20.06.2024. 60 to 70 % of questions from here. Valid questions . I achieved 914/1000.
I took this exam yesterday. The same case study questions were asked, although the ET has those questions scattered around instead of grouped together. Please note.
You should integrate Language Understanding, Text Analytics, and QnA Maker into the chatbot.