Releases: vunb/vntk
Releases · vunb/vntk
v1.4.4
v1.4.2
🔊 Release Notes
👉 Update latest [email protected]
, [email protected]
v1.4.1
v1.4.0
🔊 Release Notes
👉 Add crfsuite api, fix #38
👉 Add an example and guide how to build an NLP API Server, fix #36
👉 Update core dependencies
👉 Update readme
CRFSuite API:
var crfsuite = require('vntk').crfsuite()
var tagger = new crfsuite.Tagger()
var trainer = new crfsuite.Trainer()
Run NPL API Server
# Clone the repository
git clone https://github.com/vunb/vntk
# Move to source code folder
cd vntk
# Install dependencies
npm install
# Run NLP API server
npm run server
# Copy and paste the following link to your browser to see result in action
# http://localhost:3000/api/tok/Phó Thủ tướng Vương Đình Huệ yêu cầu điều chỉnh tên gọi “trạm thu giá” BOT
v1.3.0
🔊 Release Notes
👉 Refactor api usage convention: lowerCamelCase
for pre-trained class, UpperCamelCase
for utility class.
👉 Mark depredicated api: wordSent
, getDictionary
, Langid
.
👉 Rename wordSent to WordTokenizer
.
👉 Format tagger output for tasks: pos tagging
, chunking
, ner
.
Examples:
var vntk = require('vntk');
var ner = vntk.ner(new_model_path);
console.log(ner.tag('Chưa tiết lộ lịch trình tới Việt Nam của Tổng thống Mỹ Donald Trump', 'text'))
// Chưa tiết lộ lịch trình tới [LOC Việt Nam] của Tổng thống [LOC Mỹ] [PER Donald Trump]
VNTK v1.2.1
🔊 Release Notes
- Change api usage
- Clean dependencies
VNTK v1.2.0
✨ Major Features and Improvements
- NEW: Implement Text classification includes Bayes and fastText classifiers #18
- NEW: Implement Language Identification #26
- NEW: Implement Term Frequency–Inverse Document Frequency (tf-idf) #20
- NEW: Support nodejs version 9
🔴 Changes and Bug fixes
- Refactoring model name
- Do not support mac osx
🗎 Documentation and examples
🔊 Release Notes
- The main features in this release are: BayesClassifier, FastTextClassifier, TF-IDF, Languague Identification.
- Our experiments focus on conditional random fields and fastText models, which yield a reasonable result and fast (~20 mins per experiment).
👥 Contributors
The main models are trained in the project underthesea and fastText. Thank for their works!
VNTK v1.0.0
✨ Major Features and Improvements
- NEW: Basic features for Vietnamese NLP are implemented #15
🔴 Bug fixes
- Refactoring code project
- Remove unused package dependencies
🗎 Documentation and examples
- Demo: https://vntk.yeu.ai/
🔊 Release Notes
- The main features in this release are: tokenizer, word_sent, pos_tagging, chunking, named entitity recoginition.
- Our experiments focus on conditional random fields models, which yield a reasonable result and fast (~20 mins per experiment).
👥 Contributors
The main models are trained in the project underthesea. Thank for their works!