underthesea

Voice IPA Repository

• Demo chatbot with rasa #513
• Underthesea is great but VERY SLOW ! #185
• Lite version for underthesea #505
• Continual Learning for Vietnamese NLP - September 2021 #485

• Train model with UIT_ABSA dataset using BERT #432
• Continual Learning Challenge for Vietnamese NLP - August 2021 #434
• Fix cannot import name 'SAVE_STATE_WARNING' from 'torch.optim.lr_scheduler' #403
• Train model with UIT_ABSA dataset using GPT2 #424

This release contains open datasets and open models

• Compatible with newer version of scikit-learn (GH-313)
• Retrain classification and sentiment models with latest version of scikit-learn (GH-381)
• Add ClassifierTrainer (from languageflow) (GH-381)
• Add 3 new datasets (GH-351)
• [Funny Update] Change underthesea's avatar (GH-371)
• [CI] Add Stale App: Automatically close stale Issues and Pull Requests that tend to accumulate during a project (GH-351)

• Dependency Parsing (GH-157)
• Remove languageflow dependency (GH-364)
• Remove tabulate dependency (GH-364)
• Remove scores in text classification and sentiment section (GH-351)
• Add information of dependency_parse module in info function (GH-351)
• Try to use Github Actions (GH-353)

This release is repository for store models

• Refactor config for resources (GH-300)
• VLSP2013-WTK (⚗️-2)
• Thêm API xử lý dữ liệu (GH-299)

• Remove nltk strict version (GH-308)
• Add word_hyphen rule (GH-290)
• Sanity check python version (GH-320)

Thay đổi

• Too strict dependency specification (GH-308)
• Chức năng kiểm tra phiên bản các dependencies (GH-230)
• [sentiment bank domain] TypeError: 'NoneType' object is not iterable (GH-310)

Thay đổi

• Loại bỏ languageflow trong quá trình cài đặt (GH-295)
• Cập nhật phiên bản fasttext (GH-304)

Thanks @rain1024 for contribution

Thay đổi

• Cập nhật phiên bản fasttext 0.9.1 (GH-279)
• Smarter version numbers for denpendencies of underthesea (GH-276)
• Cải tiến tốc độ của hàm sent_tokenize (GH-280)
• Lỗi tách câu (GH-237)
• Google Colab Notebook: Underthesea v1.1.17

Ghi chú

• Release cuối cùng sử dụng languageflow

Thanks @rain1024, @TechBK for contributions

✨ Major Features and Improvements

• Improve speed of word_tokenize function
• Only support python 3.6+
• Use flake8 for style guide enforcement

Contributors

Thanks to @rain1024 for the contributions!

✨ Major Features and Improvements

🔴 Bug fixes

• Fix word_tokenize error when text contains tab (t) character
• Fix regex_tokenize with url

🔊 Release Notes

The main purpose of this release is to fix some bugs in word_tokenize and regex_tokenize functions

Contributors

Thanks to @rain1024 for the contributions!