Why translation breaks language barriers in NLP - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained translation model from Hugging Face.

NLP

from transformers import MarianMTModel, MarianTokenizer
model_name = 'Helsinki-NLP/opus-mt-en-de'
tokenizer = MarianTokenizer.from_pretrained([1])

Drag options to blanks, or click blank then click option'

A'Helsinki-NLP/opus-mt-en-de'

B'bert-base-uncased'

C'facebook/wav2vec2-base-960h'

D'gpt2'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a language model like 'bert-base-uncased' instead of a translation model.

Confusing speech models with translation models.

We use the exact model name 'Helsinki-NLP/opus-mt-en-de' to load the tokenizer for English to German translation.

2fill in blank

medium

Complete the code to tokenize the input text for translation.

NLP

text = 'Hello, how are you?'
tokenized = tokenizer([1], return_tensors='pt', padding=True)

Drag options to blanks, or click blank then click option'

Atokenizer

B'Hello, how are you?'

C['Hello', 'how', 'are', 'you']

Dtext

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a list of words instead of a string.

Passing the tokenizer object instead of the text.

We pass the variable 'text' containing the input string to the tokenizer.

3fill in blank

hard

Fix the error in generating the translated tokens.

NLP

translated_tokens = model.generate([1].input_ids, max_length=40)

Drag options to blanks, or click blank then click option'

Atext

Btokenized

Cmodel

Dtokenizer

Attempts:

3 left

💡 Hint

Common Mistakes

Passing raw text instead of token IDs.

Passing the tokenizer or model object instead of token IDs.

We use 'tokenized.input_ids' as input to the model's generate function to produce translated tokens.

4fill in blank

hard

Fill both blanks to decode the translated tokens into readable text.

NLP

translated_text = tokenizer.[1](translated_tokens[0], skip_special_tokens=[2])

Drag options to blanks, or click blank then click option'

Adecode

BTrue

CFalse

Dencode

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'encode' instead of 'decode'.

Not skipping special tokens, resulting in unwanted symbols.

We use 'decode' to convert tokens back to text and skip_special_tokens=True to remove special tokens.

5fill in blank

hard

Fill all three blanks to create a function that translates English text to German.

NLP

def translate_en_to_de(text):
    inputs = tokenizer(text, return_tensors=[1], padding=True)
    outputs = model.generate(inputs.[2], max_length=50)
    return tokenizer.[3](outputs[0], skip_special_tokens=True)

Drag options to blanks, or click blank then click option'

A'pt'

Binput_ids

Cdecode

Dtext

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'text' instead of 'input_ids' for model input.

Returning tokens without decoding.

Using wrong tensor type like 'tf' instead of 'pt'.

We use 'pt' for PyTorch tensors, 'input_ids' for model input, and 'decode' to get the translated text.

Practice

1. Why is translation important in breaking language barriers?

easy

A. It only works for spoken languages, not written ones.

B. It creates new languages for communication.

C. It removes the need for learning any language.

D. It changes text from one language to another so people can understand each other.

Solution

1. Step 1: Understand the purpose of translation

   Translation converts text or speech from one language to another to enable understanding.

2. Step 2: Identify the correct description

   It changes text from one language to another so people can understand each other correctly states that translation helps people understand each other by changing text between languages.

3. Final Answer:

   It changes text from one language to another so people can understand each other. -> Option D

4. Quick Check:

   Translation = Understanding across languages [OK]

Hint: Translation means changing language to help understanding [OK]

Common Mistakes:

• Thinking translation creates new languages
• Believing translation removes the need to learn languages
• Assuming translation only works for spoken language

2. Which of the following is the correct way to use a translation tool in Python?

easy

A. translated_text = translate('Hello', target_language='es')

B. translated_text = translate('Hello', language='es')

C. translated_text = translate('Hello', to='es')

D. translated_text = translate('Hello', lang='english')

Solution

1. Step 1: Identify correct parameter naming

   Common translation functions use 'target_language' to specify the language to translate into.

2. Step 2: Match the option with correct syntax

   translated_text = translate('Hello', target_language='es') uses 'target_language' correctly, while others use incorrect or ambiguous parameter names.

3. Final Answer:

   translated_text = translate('Hello', target_language='es') -> Option A

4. Quick Check:

   Correct parameter name = target_language [OK]

Hint: Look for 'target_language' parameter in translation functions [OK]

Common Mistakes:

• Using wrong parameter names like 'language' or 'to'
• Specifying language as 'english' instead of target code
• Confusing source and target language parameters

3. What will be the output of this Python code snippet using a simple translation dictionary?

translations = {'hello': {'es': 'hola', 'fr': 'bonjour'}}
word = 'hello'
language = 'fr'
print(translations[word][language])

medium

A. hola

B. bonjour

C. hello

D. KeyError

Solution

1. Step 1: Understand dictionary lookup

   The code looks up 'hello' in translations, then 'fr' inside that dictionary.

2. Step 2: Find the value for 'fr'

   translations['hello']['fr'] is 'bonjour'.

3. Final Answer:

   bonjour -> Option B

4. Quick Check:

   translations['hello']['fr'] = bonjour [OK]

Hint: Follow dictionary keys step-by-step to find value [OK]

Common Mistakes:

• Confusing 'es' and 'fr' keys
• Expecting original word instead of translation
• Assuming KeyError without checking keys

4. Identify the error in this translation code snippet:

def translate(word, lang):
    translations = {'hello': {'es': 'hola', 'fr': 'bonjour'}}
    return translations[word][lang]

print(translate('hello', 'de'))

medium

A. The function uses incorrect dictionary syntax.

B. The function should return the original word if translation exists.

C. The function does not handle missing language keys, causing a KeyError.

D. The function should use 'language' instead of 'lang' parameter.

Solution

1. Step 1: Analyze dictionary keys and input

   The dictionary has 'es' and 'fr' but not 'de'.

2. Step 2: Understand error cause

   Accessing translations['hello']['de'] causes KeyError because 'de' key is missing.

3. Final Answer:

   The function does not handle missing language keys, causing a KeyError. -> Option C

4. Quick Check:

   Missing key causes KeyError [OK]

Hint: Check if dictionary keys exist before accessing [OK]

Common Mistakes:

• Ignoring missing keys causing runtime errors
• Thinking dictionary syntax is wrong
• Confusing parameter names without impact

5. You want to build a translation tool that supports multiple languages and handles missing translations gracefully. Which approach best breaks language barriers effectively?

hard

A. Use a dictionary with nested language keys and return the original word if translation is missing.

B. Only translate to one language and raise errors if translation is missing.

C. Translate words randomly to any language to cover more cases.

D. Ignore missing translations and return empty strings.

Solution

1. Step 1: Consider multi-language support

   A nested dictionary allows storing translations for many languages.

2. Step 2: Handle missing translations gracefully

   Returning the original word if translation is missing avoids confusion and errors.

3. Final Answer:

   Use a dictionary with nested language keys and return the original word if translation is missing. -> Option A

4. Quick Check:

   Multi-language + graceful fallback = effective translation [OK]

Hint: Use nested dict + fallback to original word [OK]

Common Mistakes:

• Raising errors instead of fallback
• Translating randomly causing confusion
• Returning empty strings losing meaning