Python package for detecting entities in text based on a dictionary and fuzzy similarity
Project description
LexiFuzz NER: Named Entity Recognition Based on Dictionary and Fuzzy Matching
About
LexiFuzz NER is a Named Entity Recognition (NER) package designed to identify and extract named entities from unstructured text data. Leveraging a combination of dictionary-based and fuzzy matching techniques, LexiFuzz NER offers state-of-the-art accuracy in recognizing named entities in various domains, making it an invaluable tool for information extraction, natural language understanding, and text analytics.
Requirements
- Python 3.7 or Higher
- NLTK
- TheFuzz
Key Features
-
Dictionary-Based Recognition: LexiFuzz NER utilizes a comprehensive dictionary of named entities, encompassing a wide range of entities such as person names, organizations, locations, dates, and more. This dictionary is continuously updated to ensure high precision in entity recognition.
-
Fuzzy Matching: The package employs advanced fuzzy matching algorithms to identify named entities even in cases of typographical errors, misspellings, or variations in naming conventions. This ensures robustness in recognizing entities with varying textual representations.
-
Customization: LexiFuzz NER allows users to easily customize and expand the entity dictionary to suit specific domain or application requirements. This flexibility makes it adaptable to a wide array of use cases.
Usage
Manual Installation via Github
- Clone Repository
git clone https://github.com/hanifabd/lexifuzz-ner.git
- Installation
cd lexifuzz-ner && pip install .
Installation Using Pip
- Installation
pip install lexifuzz-ner
Inference
-
Usage
from lexifuzz_ner.ner import find_entity dictionary = { 'individual_product' : ['tahapan', 'xpresi', 'gold', 'berjangka'], 'brand' : ["bca", "bank central asia"] } text = "i wanna ask about bca tahapn savings product" entities = find_entity(text, dictionary, 90) print(entities)
-
Result
{ 'entities': [ { 'id': '55a20c6b-bd4a-43ee-8853-b961ac537ca8', 'entity': 'bca', 'category': 'brand', 'score': 100, 'index': {'start': 18, 'end': 20}}, { 'id': '08917da5-ed51-44bb-9be9-52f17df2640a', 'entity': 'tahapn', 'category': 'individual_product', 'score': 92, 'index': {'start': 22, 'end': 28} } ], 'text': 'i wanna ask about bca tahapn savings product', 'text_annotated': 'i wanna ask about [bca]{55a20c6b-bd4a-43ee-8853-b961ac537ca8} [tahapn]{08917da5-ed51-44bb-9be9-52f17df2640a} savings product' }
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for lexifuzz_ner-0.0.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4433d714a4e0e01eb6b74d5858fabd22a66bf12e1f70286a378212ebb6611db2 |
|
MD5 | 240d23c31dd4c857fa90438d3256e645 |
|
BLAKE2b-256 | dbb4246340a34bc438fd9cbd6217da49a6a5f8e1686909d1aaebcc00e06409de |