Exam AWS Certified Machine Learning - Specialty topic 1 question 146 discussion

D is the answer. The unrecognized words are synonyms for "comedy", so they should be added as synonyms under the comedy slot type see the excerpt: "For each intent, you can specify parameters that indicate the information that the intent needs to fulfill the user's request. These parameters, or slots, have a type. A slot type is a list of values that Amazon Lex uses to train the machine learning model to recognize values for a slot. For example, you can define a slot type called "Genres." Each value in the slot type is the name of a genre, "comedy," "adventure," "documentary," etc. You can define a synonym for a slot type value. For example, you can define the synonyms "funny" and "humorous" for the value "comedy."" https://docs.aws.amazon.com/lex/latest/dg/howitworks-custom-slots.html

D? can not be C.Amazon Lex doesn't support the AMAZON.LITERAL or the AMAZON.SearchQuery built-in slot types. https://docs.aws.amazon.com/lex/latest/dg/howitworks-builtins-slots.html

D is the answer.

The best way to fix the problem is option D, add the unrecognized words as synonyms in the custom slot type. By doing so, you can map different words that have the same meaning to the same slot value, without changing the Lambda code or data in DynamoDB. For example, you can add “funny”, “fun”, and “humor” as synonyms for the slot value “comedy”. This way, Amazon Lex can understand the category spoken by users and pass it to the Lambda function that queries the DynamoDB table for a list of book titles. Option A, adding the unrecognized words in the enumeration values list as new values in the slot type, is not a good choice because it would create new slot values that do not match the existing categories in the DynamoDB table. For example, if you add “funny” as a new value in the slot type, Amazon Lex would pass it to the Lambda function, which would not find any book titles for that category in the DynamoDB table.

C is the answer AMAZON.SearchQuery As you think about what users are likely to ask, consider using a built-in or custom slot type to capture user input that is more predictable, and the AMAZON.SearchQuery slot type to capture less-predictable input that makes up the search query. The following example shows an intent schema for SearchIntent, which uses the AMAZON.SearchQuery slot type and also includes a CityList slot that uses the AMAZON.City slot type. Make sure that your skill uses no more than one AMAZON.SearchQuery slot per intent. The Amazon.SearchQuery slot type cannot be combined with another intent slot in sample utterances. Each sample utterance must include a carrier phrase. The exception is that you can omit the carrier phrase in slot samples. A carrier phrase is the word or words that are part of the utterance, but not the slot, such as "search for" or "find out".

The ML specialist should add the unrecognized words as synonyms in the custom slot type. This will allow Amazon Lex to understand the user's intent even if they use synonyms for the predefined slot values. By adding the synonyms, Amazon Lex will recognize them as variations of the predefined slot values and map them to the appropriate slot value. This approach can be a quick and effective way to improve the accuracy of the chatbot's understanding of user requests without having to change the Lambda code or the data in DynamoDB.

B is correct