Custom pipeline components in NLP - Model Pipeline Trace

Model Pipeline - Custom pipeline components

This pipeline shows how custom components can be added to an NLP model to process text step-by-step. It starts with raw text, cleans it, extracts features, trains a model, and then makes predictions.

Data Flow - 6 Stages

1Raw Text Input

1000 rows x 1 column→Load raw sentences→1000 rows x 1 column

"I love sunny days."

↓

2Text Cleaning Component

1000 rows x 1 column→Remove punctuation and lowercase text→1000 rows x 1 column

"i love sunny days"

↓

3Custom Tokenizer Component

1000 rows x 1 column→Split sentences into word tokens→1000 rows x variable-length tokens

["i", "love", "sunny", "days"]

↓

4Feature Extraction Component

1000 rows x variable-length tokens→Convert tokens to fixed-length numeric vectors→1000 rows x 50 columns

[0.1, 0.0, 0.3, ..., 0.05]

↓

5Model Training

800 rows x 50 columns→Train classifier on training set→Trained model

Model learns to classify sentiment

↓

6Model Evaluation

200 rows x 50 columns→Evaluate model on test set→Accuracy and loss metrics

Accuracy: 0.85, Loss: 0.35

Training Trace - Epoch by Epoch

Epoch 1: *************** (loss=0.85)
Epoch 2: ************ (loss=0.65)
Epoch 3: ********* (loss=0.50)
Epoch 4: ******* (loss=0.40)
Epoch 5: ****** (loss=0.35)

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Model starts learning with moderate accuracy
2	0.65	0.72	Loss decreases, accuracy improves
3	0.50	0.80	Model gains better understanding
4	0.40	0.84	Training converges with good accuracy
5	0.35	0.87	Final epoch with best performance

Prediction Trace - 5 Layers

Layer 1: Input Text

Layer 2: Text Cleaning Component

Layer 3: Custom Tokenizer Component

Layer 4: Feature Extraction Component

Layer 5: Model Prediction

Model Quiz - 3 Questions

What does the custom tokenizer component do in the pipeline?

A Splits sentences into word tokens

B Converts tokens into numeric vectors

C Removes punctuation and lowercases text

D Trains the sentiment classifier

Key Insight

Custom pipeline components let us tailor each step of text processing and feature extraction. This helps the model learn better by preparing data exactly how we want before training and prediction.

Practice

1. What is the main purpose of a custom pipeline component in an NLP pipeline?

easy

A. To store the processed documents in a database

B. To replace the entire NLP model with a new one

C. To visualize the text data in charts

D. To add your own processing steps that modify the document

Solution

1. Step 1: Understand the role of pipeline components

   Pipeline components process text step-by-step, modifying or analyzing it.

2. Step 2: Identify what custom components do

   Custom components let you add your own processing steps that change the document or add data.

3. Final Answer:

   To add your own processing steps that modify the document -> Option D

4. Quick Check:

   Custom pipeline components = add processing steps [OK]

Hint: Custom components add steps that change the document [OK]

Common Mistakes:

• Thinking custom components replace the whole model
• Confusing visualization with processing
• Assuming storage is part of pipeline components

2. Which of the following is the correct way to define a custom pipeline component function in Python?

easy

A. def custom_component(text): return text

B. def custom_component(doc): print(doc)

C. def custom_component(doc): return doc

D. def custom_component(): return None

Solution

1. Step 1: Recall the function signature for custom components

   Custom components take a doc object and return it after processing.

2. Step 2: Check each option

   def custom_component(doc): return doc matches the signature and returns the doc. Others either take wrong input or don't return doc.

3. Final Answer:

   def custom_component(doc): return doc -> Option C

4. Quick Check:

   Function takes doc and returns doc [OK]

Hint: Custom component functions take and return doc objects [OK]

Common Mistakes:

• Using text instead of doc as input
• Not returning the doc object
• Missing the doc parameter

3. Given this custom component code:

def add_custom_attr(doc):
    for token in doc:
        token._.is_custom = token.text.isalpha()
    return doc

nlp.add_pipe(add_custom_attr, last=True)

text = 'Hello 123!'
doc = nlp(text)
print([token._.is_custom for token in doc])

What will be the printed output?

medium

A. [True, True, False]

B. [True, False, False]

C. [True, False, True]

D. [False, False, False]

Solution

1. Step 1: Analyze the tokens in the text

   The text 'Hello 123!' splits into tokens: 'Hello', '123', '!'.

2. Step 2: Check the custom attribute logic

   For each token, isalpha() returns True if all characters are letters. 'Hello' is True, '123' and '!' are False.

3. Final Answer:

   [True, False, False] -> Option B

4. Quick Check:

   isalpha() per token = [True, False, False] [OK]

Hint: Check token text with isalpha() for True/False [OK]

Common Mistakes:

• Assuming punctuation is alpha
• Counting tokens incorrectly
• Forgetting to return doc

4. What is wrong with this custom pipeline component code?

def faulty_component(doc):
    for token in doc:
        token._.is_custom = token.text.isdigit()
    # Missing return statement

nlp.add_pipe(faulty_component, last=True)

medium

A. It does not return the doc object

B. It uses an invalid attribute name

C. It modifies tokens outside the loop

D. It should not be added to the pipeline

Solution

1. Step 1: Check the function structure

   The function loops over tokens and sets a custom attribute but does not return the doc.

2. Step 2: Recall pipeline component requirements

   Custom components must return the doc object to continue the pipeline correctly.

3. Final Answer:

   It does not return the doc object -> Option A

4. Quick Check:

   Missing return doc causes pipeline failure [OK]

Hint: Always return doc at end of custom component [OK]

Common Mistakes:

• Forgetting to return doc
• Using wrong attribute names without registration
• Adding component incorrectly

5. You want to create a custom pipeline component that counts how many tokens in a document are uppercase and stores this count as doc._.uppercase_count. Which of the following is the correct approach?

hard

A. Register a doc extension for 'uppercase_count', define a component that counts uppercase tokens, assign the count to doc._.uppercase_count, and return doc

B. Add a token extension for 'uppercase_count' and count uppercase tokens per token

C. Modify tokens in place without registering any extension and return doc

D. Create a new NLP model that outputs uppercase counts directly

Solution

1. Step 1: Understand extension registration

   To add a new attribute to doc._, you must register a doc extension first.

2. Step 2: Implement counting and assignment

   Count uppercase tokens in the component, assign the count to doc._.uppercase_count, then return doc.

3. Final Answer:

   Register a doc extension for 'uppercase_count', define a component that counts uppercase tokens, assign the count to doc._.uppercase_count, and return doc -> Option A

4. Quick Check:

   Doc extension + count + assign + return doc [OK]

Hint: Register doc extension before assigning custom doc attributes [OK]

Common Mistakes:

• Not registering the doc extension before use
• Using token extension for doc-level data
• Not returning doc at the end