https://github.com/saeidsaadatigero/word-recognition

Word recognition
https://github.com/saeidsaadatigero/word-recognition

ai colab-notebook nlp-machine-learning python

Last synced: about 1 hour ago
JSON representation

Word recognition

• Host: GitHub
• URL: https://github.com/saeidsaadatigero/word-recognition
• Owner: saeidsaadatigero
• Created: 2024-10-17T19:11:21.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-11-05T15:46:19.000Z (2 months ago)
• Last Synced: 2024-11-12T20:46:41.756Z (2 months ago)
• Topics: ai, colab-notebook, nlp-machine-learning, python
• Language: Python
• Homepage:
• Size: 12.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        

# Natural Language Processing (NLP) with NLTK

This project focuses on text analysis and processing using the NLTK library in Python. The goal is to analyze text and extract key information from it.

## Steps

1. **Import Libraries**:

   First, we import the necessary libraries:

   ```python

   import nltk

   from nltk.tokenize import sent_tokenize, word_tokenize

   from nltk.corpus import stopwords

   from nltk import pos_tag

   ```

2. **Download Required Data**:

   To utilize NLTK's functionalities, we need to download some essential data:

   ```python

   nltk.download('punkt')

   nltk.download('stopwords')

   nltk.download('averaged_perceptron_tagger')

   ```

3. **Define the Text**:

   We define the text we want to process:

   ```python

   text = """

   Natural Language Processing (NLP) is a field of artificial intelligence that gives computers the ability to understand text and spoken words in much the same way human beings can.

   """

   ```

4. **Tokenize Text into Sentences and Words**:

   We split the text into sentences and words:

   ```python

   sentences = sent_tokenize(text)

   words = word_tokenize(text)

   ```

5. **Remove Stopwords**:

   We remove unnecessary words (stopwords) from the word list:

   ```python

   stop_words = set(stopwords.words('english'))

   filtered_words = [word for word in words if word.lower() not in stop_words]

   ```

6. **POS Tagging**:

   We tag the key words with their parts of speech (POS):

   ```python

   pos_tags = pos_tag(filtered_words)

   ```

7. **Display Results**:

   We display the processing results:

   ```python

   print("Sentences:", sentences)

   print("Words:", words)

   print("Filtered Words (without stopwords):", filtered_words)

   print("POS Tags:", pos_tags)

   ```