diff --git a/6-consumer/lessons/4-multiple-language-support/README.md b/6-consumer/lessons/4-multiple-language-support/README.md index 09f42a9c..45e84c85 100644 --- a/6-consumer/lessons/4-multiple-language-support/README.md +++ b/6-consumer/lessons/4-multiple-language-support/README.md @@ -44,7 +44,7 @@ For example, translating "Hello world" from English into French can be performed Substitutions don't work when different languages use different ways of saying the same thing. For example, the English sentence "My name is Jim", translates into "Je m'appelle Jim" in French - literally "I call myself Jim". "Je" is French for "I", "moi" is me, but is concatenated with the verb as it starts with a vowel, so becomes "m'", "appelle" is to call, and "Jim" isn't translated as it's a name, and not a word that can be translated. Word ordering also becomes an issue - a simple substitution of "Je m'appelle Jim" becomes "I myself call Jim", with a different word order to English. -> 💁 Some words are never translated - my name is Jim regardless of which language is used to introduce me. +> 💁 Some words are never translated - my name is Jim regardless of which language is used to introduce me. When translating to languages that use different alphabets, or use different letters for different sounds, then words can be *transliterated*, that is selecting letters or characters that give the appropriate sound to sound the same as the given word. Idioms are also a problem for translation. These are phrases that have an understood meaning that is different from a direct interpretation of the words. For example, in English the idiom "I've got ants in my pants" does not literally refer to having ants in your clothing, but to being restless. If you translated this to German, you would end up confusing the listener, as the German version is "I have bumble bees in the bottom". diff --git a/images/Diagrams.sketch b/images/Diagrams.sketch index aa14d58c..53c08897 100644 Binary files a/images/Diagrams.sketch and b/images/Diagrams.sketch differ diff --git a/images/fruit-quality-detector-message-flow.png b/images/fruit-quality-detector-message-flow.png index 311a527f..e76e9a37 100644 Binary files a/images/fruit-quality-detector-message-flow.png and b/images/fruit-quality-detector-message-flow.png differ diff --git a/quiz-app/src/assets/translations/en.json b/quiz-app/src/assets/translations/en.json index 4580cb1a..28c17c9a 100644 --- a/quiz-app/src/assets/translations/en.json +++ b/quiz-app/src/assets/translations/en.json @@ -1622,7 +1622,7 @@ }, { "id": 33, - "title": "Lesson 17 - Run your fruit detector on the edge: Pre-Lecture Quiz", + "title": "Lesson 17 - Run your fruit detector on the edge: Pre-Lecture Quiz", "quiz": [ { "questionText": "Edge computing can be more secure than cloud computing.", @@ -1667,7 +1667,7 @@ }, { "id": 34, - "title": "Lesson 17 - Run your fruit detector on the edge: Post-Lecture Quiz", + "title": "Lesson 17 - Run your fruit detector on the edge: Post-Lecture Quiz", "quiz": [ { "questionText": "What kind of format or domain do we need for Custom Vision ML models to properly run on an edge device?", @@ -1737,6 +1737,724 @@ ] } ] + }, + { + "id": 35, + "title": "Lesson 18 - Trigger fruit quality detection from a sensor: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "Which part of your IoT application gathers data?", + "answerOptions": [ + { + "answerText": "Things", + "isCorrect": "true" + }, + { + "answerText": "Cloud services", + "isCorrect": "false" + }, + { + "answerText": "Edge devices", + "isCorrect": "false" + } + ] + }, + { + "questionText": "The only outputs of an IoT application are actuators.", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Things don't need to connect directly to IoT Hub, they can use edge devices as gateways.", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "true" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 36, + "title": "Lesson 18 - Trigger fruit quality detection from a sensor: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "The three components of architecting an IoT application are", + "answerOptions": [ + { + "answerText": "Things, Insights, Actions", + "isCorrect": "true" + }, + { + "answerText": "Things, Internet, Databases", + "isCorrect": "false" + }, + { + "answerText": "AI, Blockchain, FizzBuzzers", + "isCorrect": "false" + } + ] + }, + { + "questionText": "The component that communicates between the things and the components that create insights is:", + "answerOptions": [ + { + "answerText": "Azure Functions", + "isCorrect": "false" + }, + { + "answerText": "IoT Hub", + "isCorrect": "true" + }, + { + "answerText": "Azure Maps", + "isCorrect": "false" + } + ] + }, + { + "questionText": "How do time of flight proximity sensors work?", + "answerOptions": [ + { + "answerText": "They send laser beams and time how long till they bounce off an object", + "isCorrect": "true" + }, + { + "answerText": "They use sound and measure how long till the sound bounces off an object", + "isCorrect": "false" + }, + { + "answerText": "They use very large rulers", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 37, + "title": "Lesson 19 - Train a stock detector: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "AI models cannot be used to count objects?", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "IoT and AI can be used in retail for:", + "answerOptions": [ + { + "answerText": "Stock checking only", + "isCorrect": "false" + }, + { + "answerText": "A wide range of uses including stock checking, monitoring for mask where where required, tracking footfall, automated billing", + "isCorrect": "true" + }, + { + "answerText": "IoT and AI cannot be used in retail", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Object detection involves:", + "answerOptions": [ + { + "answerText": "Detecting objects in an image and tracking their location and probability", + "isCorrect": "true" + }, + { + "answerText": "Counting objects in an image only", + "isCorrect": "false" + }, + { + "answerText": "Classifying images", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 38, + "title": "Lesson 19 - Train a stock detector: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "Object detectors only return one result no matter how many objects are detected", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + }, + { + "questionText": "What is the best domain to use in Custom Vision for stock counting", + "answerOptions": [ + { + "answerText": "General", + "isCorrect": "false" + }, + { + "answerText": "Food", + "isCorrect": "false" + }, + { + "answerText": "Products on shelves", + "isCorrect": "true" + } + ] + }, + { + "questionText": "At least how many images do you need to train an object detector?", + "answerOptions": [ + { + "answerText": "1", + "isCorrect": "false" + }, + { + "answerText": "15", + "isCorrect": "true" + }, + { + "answerText": "100", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 39, + "title": "Lesson 20 - Check stock from an IoT device: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "IoT devices are not powerful enough to use object detectors", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Object detectors give you:", + "answerOptions": [ + { + "answerText": "The count of objects detected", + "isCorrect": "false" + }, + { + "answerText": "The count and location of objects detected", + "isCorrect": "false" + }, + { + "answerText": "The count, location and probability of objects detected", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Object detectors can be used to detect where missing stock should be to allow robots to automatically stock shelves", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "true" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 40, + "title": "Lesson 20 - Check stock from an IoT device: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "To count stock you only need to consider the count of objects detected by the object detector", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Bounding boxes use:", + "answerOptions": [ + { + "answerText": "Percentage based coordinates", + "isCorrect": "true" + }, + { + "answerText": "Pixel based coordinates", + "isCorrect": "false" + }, + { + "answerText": "Centimeter based coordinates", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Can detected objects overlap?", + "answerOptions": [ + { + "answerText": "Yes", + "isCorrect": "true" + }, + { + "answerText": "No", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 41, + "title": "Lesson 21 - Recognize speech with an IoT device: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "IoT devices can be used to recognize speech:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "true" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Voice assistants should send all the audio they hear to the cloud for processing:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "To recognize speech, IoT devices need large microphones:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 42, + "title": "Lesson 21 - Recognize speech with an IoT device: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "Microphones are what type of sensor?", + "answerOptions": [ + { + "answerText": "Digital", + "isCorrect": "false" + }, + { + "answerText": "Analog", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Sound waves are converted to digital signals using:", + "answerOptions": [ + { + "answerText": "Pulse Code Modulation", + "isCorrect": "true" + }, + { + "answerText": "Pure Code Multiplication", + "isCorrect": "false" + }, + { + "answerText": "Pulse Width Maximization", + "isCorrect": "false" + } + ] + }, + { + "questionText": "1 second of 16-bit audio sampled at 16KHz is how large?", + "answerOptions": [ + { + "answerText": "1KB", + "isCorrect": "false" + }, + { + "answerText": "16KB", + "isCorrect": "false" + }, + { + "answerText": "32KB", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 43, + "title": "Lesson 22 - Understand language: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "Language understanding involves looking for fixed words:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Language understanding involves:", + "answerOptions": [ + { + "answerText": "Looking at the individual words in a sentence and trying to get the meaning", + "isCorrect": "false" + }, + { + "answerText": "Finding pre-defined sentences and using those to get the meaning", + "isCorrect": "false" + }, + { + "answerText": "Looking at the whole sentence and trying to get the meaning using the context of the words", + "isCorrect": "true" + } + ] + }, + { + "questionText": "Cloud providers have AI services that can understand language:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "true" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 44, + "title": "Lesson 22 - Understand language: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "Sentences are understood by being broken down into:", + "answerOptions": [ + { + "answerText": "Ideas and explanations", + "isCorrect": "false" + }, + { + "answerText": "Intents and entities", + "isCorrect": "true" + }, + { + "answerText": "Imps and elves", + "isCorrect": "false" + } + ] + }, + { + "questionText": "The Microsoft service for language understanding is called:", + "answerOptions": [ + { + "answerText": "LUIS", + "isCorrect": "true" + }, + { + "answerText": "Luigi", + "isCorrect": "false" + }, + { + "answerText": "Jarvis", + "isCorrect": "false" + } + ] + }, + { + "questionText": "In the sentence 'set a 3 minute timer' the:", + "answerOptions": [ + { + "answerText": "The intent is 3 minutes and the entity is a timer", + "isCorrect": "false" + }, + { + "answerText": "The intent is minutes, and the entity is 3 timers", + "isCorrect": "false" + }, + { + "answerText": "The intent is set a timer and the entity is 3 minutes", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 45, + "title": "Lesson 23 - Set a timer and provide spoken feedback: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "Speech generated by AI models sounds monotonous and robotic", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "AI models can only create speech in American English:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "AI models would convert 1234 into which spoken phrase:", + "answerOptions": [ + { + "answerText": "One two three four", + "isCorrect": "false" + }, + { + "answerText": "One thousand two hundred and thirty four", + "isCorrect": "false" + }, + { + "answerText": "It can be 'one two three four' or 'one thousand two hundred and thirty four' depending on the context", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 46, + "title": "Lesson 23 - Set a timer and provide spoken feedback: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "The three parts of speech generation are:", + "answerOptions": [ + { + "answerText": "Text analysis, understanding analysis, sound generation", + "isCorrect": "false" + }, + { + "answerText": "Text analysis, linguistic analysis, wave form generation", + "isCorrect": "true" + }, + { + "answerText": "Word analysis, audio production", + "isCorrect": "false" + } + ] + }, + { + "questionText": "Can speech generation models be trained to sound like existing people:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "true" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + }, + { + "questionText": "The markup language used to encode speech is called:", + "answerOptions": [ + { + "answerText": "SSML", + "isCorrect": "true" + }, + { + "answerText": "MSSL", + "isCorrect": "false" + }, + { + "answerText": "SpeechXML", + "isCorrect": "false" + } + ] + } + ] + }, + { + "id": 47, + "title": "Lesson 24 - Support multiple languages: Pre-Lecture Quiz", + "quiz": [ + { + "questionText": "Language understanding only understands English:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "False", + "isCorrect": "true" + } + ] + }, + { + "questionText": "AI speech to text models understand multiple languages:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "true" + }, + { + "answerText": "False", + "isCorrect": "false" + } + ] + }, + { + "questionText": "AI translation involves swapping individual words for their translated version:", + "answerOptions": [ + { + "answerText": "True", + "isCorrect": "false" + }, + { + "answerText": "false", + "isCorrect": "true" + } + ] + } + ] + }, + { + "id": 48, + "title": "Lesson 24 - Support multiple languages: Post-Lecture Quiz", + "quiz": [ + { + "questionText": "Machine translation has been researched for nearly:", + "answerOptions": [ + { + "answerText": "70 years", + "isCorrect": "true" + }, + { + "answerText": "17 years", + "isCorrect": "false" + }, + { + "answerText": "7 years", + "isCorrect": "false" + } + ] + }, + { + "questionText": "AI language translators are called:", + "answerOptions": [ + { + "answerText": "Noddy translators", + "isCorrect": "false" + }, + { + "answerText": "Neural translators", + "isCorrect": "true" + }, + { + "answerText": "Nothing - AI cannot be used for translation", + "isCorrect": "false" + } + ] + }, + { + "questionText": "What alien languages does the Microsoft translator support:", + "answerOptions": [ + { + "answerText": "Na'vi", + "isCorrect": "false" + }, + { + "answerText": "Alienese", + "isCorrect": "false" + }, + { + "answerText": "Klingon", + "isCorrect": "true" + } + ] + } + ] } ] }