You are developing the chatbot.
You create the following components:
✑ A QnA Maker resource
✑ A chatbot by using the Azure Bot Framework SDK
You need to add an additional component to meet the technical requirements and the chatbot requirements.
What should you add?
To meet the technical requirements, which include supporting English, French, and Portuguese, the appropriate component to add is Language Understanding (LUIS). LUIS allows the bot to understand the user's intent in multiple languages and provides the capability to handle alternative responses when the response confidence score is low. Microsoft Translator could handle translation but does not manage intent understanding. Orchestrator is used for routing messages to different bots or processes, which is more complex than the need specified. Chatdown is a tool for creating mockups and does not meet the functional requirement.
B. Language Understanding Explanation: To meet the requirement that the chatbot must support English, French, and Portuguese and provide other response options when the response confidence score is low, the Language Understanding component (often referred to as LUIS - Language Understanding Intelligent Service) is needed. LUIS allows the bot to understand the user's intent in multiple languages and can help to provide alternative responses. Microsoft Translator could translate between languages, but it does not handle intent understanding, so it's not the best choice here. Orchestrator is more about managing multiple LUIS and QnA Maker models, which isn't specified in the requirements. Chatdown is a tool for creating mockups of chatbot conversations but doesn't provide the functionality needed to meet the requirements.
Correct! Thank you. https://learn.microsoft.com/en-us/azure/ai-services/luis/luis-language-support#multilingual-luis-apps If you need a multilingual LUIS client application such as a chatbot, you have a few options. If LUIS supports all the languages, you develop a LUIS app for each language. Each LUIS app has a unique app ID, and endpoint log. If you need to provide language understanding for a language LUIS does not support, you can use the Translator service to translate the utterance into a supported language, submit the utterance to the LUIS endpoint, and receive the resulting scores.
thanks for reference
I think you are right!
A is correct answer. "If you need to support a knowledge base system, which includes several languages, you can: 1) Use the Translator service to translate a question into a single language before sending the question to your knowledge base. This allows you to focus on the quality of a single language and the quality of the alternate questions and answers. 2) Create a QnA Maker resource, and a knowledge base inside that resource, for every language. This allows you to manage separate alternate questions and answer text that is more nuanced for each language. This gives you much more flexibility but requires a much higher maintenance cost when the questions or answers change across all languages." https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/language-support#supporting-multiple-languages-in-one-knowledge-base
Scenario: Text-based content is provided only in one language and is not translated. Hence, translator may not be required
C. Orchestrator: Orchestrator is a component of the Bot Framework responsible for routing messages to different bots or processes based on the context or content of the conversation. It can help in managing complex scenarios where multiple bots or services are involved, such as switching between the FAQ bot and a live agent chat, or handling low-confidence responses by offering alternative options or escalating to human agents. This component is crucial for managing the flow of conversation based on AI confidence scores and ensuring that users can be directed to a customer service agent when needed.
FAQs is only available in English and there are no multi-language support required for the chat bot. You need dispatching capability however as you need to provide a way to talk to a agent and integrate with Omnichannel for Customer Service.
I think correct answer is B. Technical and Chatbot requirement have in common the behaviour to be taken in case of confidence score lower than 70%. Particularly one of the chatbot requirements is: "When the response confidence score is low, ensure that the chatbot can provide other response options to the customers". And LUIS fits the bill https://learn.microsoft.com/en-us/azure/ai-services/luis/luis-language-support#multilingual-luis-apps
Use translator service to support multiple languages
Orchestrator is a replacement for the now deprecated Bot Framework Dispatcher.
To meet both the technical and chatbot requirements, you should add Language Understanding (LUIS) to your chatbot solution.
https://learn.microsoft.com/en-us/azure/ai-services/qnamaker/overview/language-support#:~:text=to%20a%20query.-,Supporting%20multiple%20languages%20in%20one%20QnA%20Maker%20resource,maintenance%20cost%20when%20the%20questions%20or%20answers%20change%20across%20all%20languages.,-Languages%20supported
A. Microsoft Translator Here's why: Technical requirements: All projects must support English, French, and Portuguese. Chatbot requirements: Provide answers to FAQs and chat with customers in English, French, and Portuguese.
Orchestrator is the correct answer while the other choices are very close to being the right answer as well
must be A
B. is the closest. Q&A Maker will become custom question answering within AI language. https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/tutorials/multiple-languages The language for the incoming user query can be detected with the Language Detection API and the user can call the appropriate endpoint and project depending on the detected language.
Microsoft Translator
C is correct answer.
It should be Language understanding, that can cover all the scenarios - understanding utterances, intents, language detection etc https://learn.microsoft.com/en-gb/training/modules/build-language-understanding-model/2a-understand-prebuilt-capabilities
Selected Answer: B