Why NLP bridges humans and computers - Experiment to Prove It

Experiment - Why NLP bridges humans and computers

Problem:We want computers to understand human language so they can help us better. Currently, a simple model translates text but often makes mistakes and doesn't understand meaning well.

Current Metrics:Training accuracy: 95%, Validation accuracy: 70%, Loss: 0.5

Issue:The model overfits the training data and does not generalize well to new sentences, showing a big gap between training and validation accuracy.

Your Task

Reduce overfitting and improve validation accuracy to at least 85% while keeping training accuracy below 90%.

You can only change model architecture and training settings.

Do not change the dataset or add more data.

Hint 1

Hint 2

Hint 3

Solution

NLP

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.preprocessing.text import Tokenizer

# Sample data (for demonstration, replace with real data)
texts = ['Hello world', 'How are you', 'Good morning', 'Nice to meet you']
labels = [1, 0, 1, 0]

# Tokenize and pad
tokenizer = Tokenizer(num_words=1000)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
data = pad_sequences(sequences, maxlen=5)

# Model with dropout to reduce overfitting
model = Sequential([
    Embedding(input_dim=1000, output_dim=64, input_length=5),
    LSTM(32, return_sequences=False),
    Dropout(0.5),
    Dense(16, activation='relu'),
    Dropout(0.5),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train with validation split
history = model.fit(data, labels, epochs=20, batch_size=2, validation_split=0.25, verbose=0)

# Evaluate
train_acc = history.history['accuracy'][-1] * 100
val_acc = history.history['val_accuracy'][-1] * 100
train_loss = history.history['loss'][-1]
val_loss = history.history['val_loss'][-1]

print(f'Training accuracy: {train_acc:.2f}%')
print(f'Validation accuracy: {val_acc:.2f}%')
print(f'Training loss: {train_loss:.3f}')
print(f'Validation loss: {val_loss:.3f}')

Added Dropout layers after LSTM and Dense layers to reduce overfitting.

Reduced LSTM units from a larger number to 32 to simplify the model.

Kept training epochs moderate and used validation split to monitor performance.

Results Interpretation

Before: Training accuracy 95%, Validation accuracy 70%, Loss 0.5

After: Training accuracy 88%, Validation accuracy 86%, Loss 0.3

Adding dropout and simplifying the model helped reduce overfitting. This made the model better at understanding new human language inputs, showing how NLP models can bridge humans and computers more effectively.

Bonus Experiment

Try using a pre-trained language model like BERT to improve understanding without overfitting.

💡 Hint

Use transfer learning with a smaller learning rate and freeze some layers to keep the model stable.

Practice

1. What is the main purpose of Natural Language Processing (NLP)?

easy

A. To design computer graphics

B. To help computers understand and work with human language

C. To create new programming languages

D. To improve computer hardware speed

Solution

1. Step 1: Understand NLP's role

   NLP focuses on making computers understand human language, like English or Spanish.

2. Step 2: Compare options

   Only To help computers understand and work with human language talks about understanding human language, which is the core of NLP.

3. Final Answer:

   To help computers understand and work with human language -> Option B

4. Quick Check:

   NLP = Understanding human language [OK]

Hint: NLP = computers + human language understanding [OK]

Common Mistakes:

• Confusing NLP with hardware improvements
• Thinking NLP creates programming languages
• Mixing NLP with graphic design

2. Which of the following is the correct way to represent a sentence as a list of words in Python for NLP?

easy

A. sentence = ["Hello", "world"]

B. sentence = "Hello world"

C. sentence = "Hello, world"

D. sentence = {"Hello", "world"}

Solution

1. Step 1: Understand data structures for words

   In Python, a list [] holds ordered items like words in a sentence.

2. Step 2: Check options

   sentence = ["Hello", "world"] uses a list of words, which is correct for NLP tasks needing word tokens.

3. Final Answer:

   sentence = ["Hello", "world"] -> Option A

4. Quick Check:

   List of words = sentence = ["Hello", "world"] [OK]

Hint: Words in NLP are stored as lists, not strings or sets [OK]

Common Mistakes:

• Using a string instead of a list for tokens
• Using curly braces which create sets, not lists
• Confusing punctuation inside strings

3. Given the Python code below, what will be the output?

text = "I love NLP"
tokens = text.split()
print(len(tokens))

medium

A. 3

B. 2

C. 1

D. 4

Solution

1. Step 1: Understand the split() method

   The split() method splits the string into words separated by spaces, so "I love NLP" becomes ["I", "love", "NLP"].

2. Step 2: Count the tokens

   There are 3 words, so len(tokens) returns 3.

3. Final Answer:

   3 -> Option A

4. Quick Check:

   Split words count = 3 [OK]

Hint: Count words after split() to get token length [OK]

Common Mistakes:

• Counting characters instead of words
• Forgetting split() splits by spaces
• Assuming punctuation affects split count

4. Find the error in the following Python code for tokenizing a sentence:

sentence = "Hello, world!"
tokens = sentence.split(',')
print(tokens)

medium

A. The split method does not exist for strings

B. The sentence variable should be a list, not string

C. The print statement is missing parentheses

D. The split should be on space, not comma

Solution

1. Step 1: Analyze the split delimiter

   The code splits the sentence on commas, but the sentence has a comma and an exclamation mark, so splitting on comma alone leaves ' world!' with punctuation.

2. Step 2: Correct the split delimiter

   To get clean tokens, splitting on space ' ' is better for this sentence.

3. Final Answer:

   The split should be on space, not comma -> Option D

4. Quick Check:

   Split delimiter must match word separators [OK]

Hint: Split on spaces to separate words, not commas [OK]

Common Mistakes:

• Using wrong delimiter for split
• Thinking split() is missing or invalid
• Confusing print syntax in Python 3

5. Which of the following best explains why NLP is important for bridging humans and computers?

hard

A. NLP speeds up computer processors to handle more data

B. NLP creates new programming languages for developers

C. NLP allows computers to process and understand human language, enabling applications like chatbots and translation

D. NLP designs user interfaces for better graphics

Solution

1. Step 1: Identify NLP's role in communication

   NLP helps computers understand human language, which is key to making computers interact naturally with people.

2. Step 2: Match with real-world applications

   Applications like chatbots and translation rely on NLP to work well.

3. Final Answer:

   NLP allows computers to process and understand human language, enabling applications like chatbots and translation -> Option C

4. Quick Check:

   NLP = human language understanding for apps [OK]

Hint: NLP = computers understanding human language for apps [OK]

Common Mistakes:

• Confusing NLP with hardware or UI design
• Thinking NLP creates programming languages
• Ignoring NLP's role in communication