Exam AI-102 topic 3 question 79 discussion

To minimize the number of utterances needed for training when many intents share similar utterances with variable airport names or codes, you should use the Pattern.any custom entity. This entity type allows you to define patterns with placeholders for variable parts (like airport names/codes), reducing the need to enumerate every possible utterance variation. Suppose you have intents like: BookFlight CheckFlightStatus And users might say things like: "Book a flight to JFK" "Book a flight to London Heathrow" "Check the status of flight DL123" "Check the status of flight to SFO" The variable parts are airport names, airport codes, or flight numbers. You define a Pattern.any entity called, for example, @destination or @flightCode. Intent: BookFlight Pattern: "Book a flight to {@destination}" Intent: CheckFlightStatus Pattern: "Check the status of flight {@flightCode}" "Check the status of flight to {@destination}"

Pattern.any is CORRECT because it is used to identify entities that can have multiple forms, such as "John F. Kennedy International Airport" or "JFK." In this case, the Pattern.any entity allows the Language Understanding model to recognize both full airport names and their corresponding codes as the same entity, without needing to list every possible variation in the training utterances. This approach minimizes the number of utterances required and ensures consistent entity recognition. https://learn.microsoft.com/en-us/azure/ai-services/luis/concepts/patterns-features#patternany-entity I would go for A

Either A or D, both works. A less development effort, D a better solution. However, the requirement is not talking about minimizing development efforts.

Either A or D, both works. A less development effort, D a better solution. Howeve,r the requirements it is not talking to minimize development effort.

pattern.any https://learn.microsoft.com/ja-jp/azure/ai-services/luis/reference-entity-pattern-any?tabs=V2 list https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/entity-components

List: fixed, close set of related words

It shoul be LIST

D. List https://learn.microsoft.com/en-us/azure/ai-services/luis/reference-entity-list?tabs=V2 Suppose the app has a list, named Cities, allowing for variations of city names including city of airport (Sea-tac), airport code (SEA), postal zip code (98101), and phone area code (206). List item Item synonyms Seattle sea-tac, sea, 98101, 206, +1 Paris cdg, roissy, ory, 75001, 1, +33 book 2 tickets to paris In the previous utterance, the word paris is mapped to the paris item as part of the Cities list entity. The list entity matches both the item's normalized name as well as the item synonyms.

LIST entity

USing a list entity allows you to define a set of values and their synonyms which will help minimize the number of utterances needed to train the model. Hence the answer must be: D) List

Pattern, you can use this to summarise multiple utterances into intents

"Patterns are designed to improve accuracy when multiple utterances are very similar. A pattern allows you to gain more accuracy for an intent without providing several more utterances." So, it has to be pattern. The only one in the list is Pattern.Any. Looks like the MIcrosoft guy just read this line and made the question and randomly chose a pattern type

Copied entire question to Copilot, and Copilot says D. To minimize the number of utterances used to train the model, you should use a list entity. List entities allow you to define a list of values (such as airport names or codes) and associate them with a single entity. This way, you can handle multiple similar utterances with a single entity reference, making your model more efficient and concise.

Pattern.any according to Copilot

Answer is A according to ChatGPT

A. Pattern Any From: https://learn.microsoft.com/en-us/azure/ai-services/luis/concepts/patterns-features#patternany-entity For Airports this means: You can exrpess the Airport Name in Full as "John F. Kennedy International Airport" or in short with the code as "JFK" LUIS will have to get both as the same

as per chat gpt: To minimize the number of utterances used to train the model while dealing with similar utterances containing airport names or airport codes, you should use a custom entity that can generalize the variations of the entities within the utterances. The correct choice in this scenario is Pattern.any. Pattern.any is used in Language Understanding (LUIS) to handle cases where you have a specific pattern in the utterances, but the specific instances of an entity (like airport names or codes) can vary widely. By using Pattern.any, you can define a pattern that recognizes and extracts any airport name or code without needing to provide all possible variations in the training data. Therefore, the most suitable option is: A. Pattern.any