Data extraction from text in Prompt Engineering / GenAI - Model Pipeline Trace

Model Pipeline - Data extraction from text

This pipeline takes raw text and finds useful pieces of information inside it. It cleans the text, finds important words or phrases, and then uses a model to pick out the data we want.

Data Flow - 6 Stages

1Raw Text Input

1000 sentences x variable length→Receive raw text data from documents or messages→1000 sentences x variable length

"John bought 3 apples on Monday."

↓

2Text Cleaning

1000 sentences x variable length→Remove punctuation, lowercase all words, remove extra spaces→1000 sentences x variable length

"john bought 3 apples on monday"

↓

3Tokenization

1000 sentences x variable length→Split sentences into words or tokens→1000 sentences x average 7 tokens

["john", "bought", "3", "apples", "on", "monday"]

↓

4Feature Extraction

1000 sentences x average 7 tokens→Convert tokens into numbers using word embeddings→1000 sentences x 7 tokens x 50 features

[[0.12, -0.05, ..., 0.33], ..., [0.01, 0.22, ..., -0.11]]

↓

5Model Prediction

1000 sentences x 7 tokens x 50 features→Use trained model to identify data entities in text→1000 sentences x 7 tokens x 3 classes (entity tags)

["B-PER", "O", "B-QUANTITY", "B-ITEM", "O", "B-DATE"]

↓

6Data Extraction Output

1000 sentences x 7 tokens x 3 classes→Convert tagged tokens into structured data entries→1000 structured records

{"Person": "John", "Quantity": 3, "Item": "apples", "Date": "Monday"}

Training Trace - Epoch by Epoch

1.2 |**************
0.9 |**********
0.7 |*******
0.5 |****
0.4 |***
    +----------------
     1  2  3  4  5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.55	Model starts learning, loss high, accuracy low
2	0.9	0.68	Loss decreases, accuracy improves
3	0.7	0.75	Model learns important patterns
4	0.5	0.82	Good improvement, model converging
5	0.4	0.87	Loss low, accuracy high, training stable

Prediction Trace - 5 Layers

Layer 1: Input Text

Layer 2: Tokenization

Layer 3: Embedding Layer

Layer 4: Model Prediction

Layer 5: Data Structuring

Model Quiz - 3 Questions

What happens to the text during the 'Text Cleaning' stage?

A Punctuation is removed and text is lowercased

B Text is split into tokens

C Model predicts entity tags

D Structured data is created

Key Insight

This visualization shows how raw text is cleaned, turned into numbers, and then a model learns to find useful data inside. As training goes on, the model gets better at tagging words correctly, which helps us extract structured information from messy text.

Practice

1. What is the main goal of data extraction from text in AI?

easy

A. To find and pull out useful information like names and dates from text

B. To translate text from one language to another

C. To generate new text based on a prompt

D. To compress text files to save space

Solution

1. Step 1: Understand the purpose of data extraction

   Data extraction means finding specific useful info inside text, such as names, dates, or places.

2. Step 2: Compare options to the definition

   Only To find and pull out useful information like names and dates from text matches this purpose exactly, while others describe different tasks like translation or compression.

3. Final Answer:

   To find and pull out useful information like names and dates from text -> Option A

4. Quick Check:

   Data extraction = find useful info [OK]

Hint: Look for the option about finding info inside text [OK]

Common Mistakes:

• Confusing extraction with translation
• Thinking extraction means generating new text
• Mixing extraction with file compression

2. Which of the following is the correct way to call a function extract_entities with a text input doc in Python?

easy

A. extract_entities = doc()

B. extract_entities(doc)

C. extract_entities.doc()

D. extract_entities->doc()

Solution

1. Step 1: Recall Python function call syntax

   In Python, to call a function with an argument, use function_name(argument).

2. Step 2: Check each option

   extract_entities(doc) uses correct syntax: extract_entities(doc). Options A, C, and D are invalid Python syntax for calling a function.

3. Final Answer:

   extract_entities(doc) -> Option B

4. Quick Check:

   Function call = function_name(argument) [OK]

Hint: Remember Python calls use parentheses with arguments inside [OK]

Common Mistakes:

• Using dot notation to call a function
• Assigning function call to function name
• Using arrow notation like other languages

3. Given this Python code using a simple extraction model:

text = "Alice met Bob on 2023-04-01 in Paris."
entities = extract_entities(text)
print(entities)

If extract_entities returns a list of tuples with (entity, type), what is the expected output?

medium

A. {'Alice': 'PERSON', 'Bob': 'PERSON', '2023-04-01': 'DATE', 'Paris': 'LOCATION'}

B. ['Alice', 'Bob', '2023-04-01', 'Paris']

C. None

D. [('Alice', 'PERSON'), ('Bob', 'PERSON'), ('2023-04-01', 'DATE'), ('Paris', 'LOCATION')]

Solution

1. Step 1: Understand the function output format

   The function returns a list of tuples, each tuple has (entity, type).

2. Step 2: Match output to expected format

   [('Alice', 'PERSON'), ('Bob', 'PERSON'), ('2023-04-01', 'DATE'), ('Paris', 'LOCATION')] matches a list of tuples with entity and type pairs. ['Alice', 'Bob', '2023-04-01', 'Paris'] is just a list of strings, A is a dictionary, and D is None.

3. Final Answer:

   [('Alice', 'PERSON'), ('Bob', 'PERSON'), ('2023-04-01', 'DATE'), ('Paris', 'LOCATION')] -> Option D

4. Quick Check:

   List of (entity, type) tuples = [('Alice', 'PERSON'), ('Bob', 'PERSON'), ('2023-04-01', 'DATE'), ('Paris', 'LOCATION')] [OK]

Hint: Look for list of tuples format with entity and type [OK]

Common Mistakes:

• Confusing list of strings with list of tuples
• Expecting dictionary instead of list
• Assuming function returns None

4. You have this code snippet:

def extract_entities(text):
    entities = []
    for word in text.split():
        if word.istitle():
            entities.append((word, 'PERSON'))
    return entities

text = "John and Mary went to London."
print(extract_entities(text))

What is the bug in this code for extracting entities?

medium

A. It only detects words starting with uppercase, missing multi-word names

B. It does not split text into words

C. It returns a string instead of a list

D. It crashes because of missing import

Solution

1. Step 1: Analyze the extraction logic

   The code checks if each word starts with uppercase (istitle) and labels it as 'PERSON'.

2. Step 2: Identify limitation

   This misses multi-word names like 'New York' or full names with multiple words. It only detects single capitalized words.

3. Final Answer:

   It only detects words starting with uppercase, missing multi-word names -> Option A

4. Quick Check:

   Single-word detection limitation = It only detects words starting with uppercase, missing multi-word names [OK]

Hint: Check if code handles multi-word names or just single words [OK]

Common Mistakes:

• Thinking split() is missing
• Assuming return type is wrong
• Expecting import needed for this code

5. You want to extract dates and locations from a large text using a pretrained AI model. Which approach best improves accuracy and speed?

hard

A. Use a generic language model without any fine-tuning

B. Manually write rules to find dates and locations using string matching

C. Use a named entity recognition (NER) model fine-tuned on your domain data

D. Extract all capitalized words as locations and all numbers as dates

Solution

1. Step 1: Consider model choice for extraction

   Fine-tuning a NER model on your specific domain helps it learn patterns and improves accuracy.

2. Step 2: Compare other options

   Manual rules are slow and brittle, generic models lack domain knowledge, and simple heuristics miss many cases.

3. Final Answer:

   Use a named entity recognition (NER) model fine-tuned on your domain data -> Option C

4. Quick Check:

   Fine-tuned NER model = best accuracy and speed [OK]

Hint: Fine-tune NER models for best extraction results [OK]

Common Mistakes:

• Relying on manual rules only
• Using generic models without tuning
• Using simple heuristics that miss cases