underthesea icon indicating copy to clipboard operation
underthesea copied to clipboard

Underthesea - Vietnamese NLP Toolkit

Results 79 underthesea issues
Sort by recently updated
recently updated
newest added

Discussion thread about `ideas` and `features` of underthesea version **6** ## 6.1 (2023-02-26) * GH-502 * GH-588 * GH-648 * GH-641 ## 6.0 (2023-01-25) * GH-622 * GH-607 * GH-621...

🍯 This issue is to track my new idea: App `Underthesea` 🗣️ I always want to create an continual learning app (GH-529, GH-516, GH-485), where I can manage articles and...

app-underthesea

![image](https://user-images.githubusercontent.com/66482009/220251449-f6153586-c71a-40c6-b67a-0006309502b6.png) My Input is copied from the example but the output is different. Could you please take a look? OS: Ubuntu 20.04 Python: 3.8.10 pip: 20.0.2

module: named_entity_recognition

**Plan** 1. Gather resources: - [x] Collect Vietnamese dictionaries, linguistic studies, and other resources that contain information on Vietnamese syllables. 2. Analysis of the resources: - [ ] Analyze the...

corpus
module: ipa

I want to create a new dataset specifically designed to support the development of a chatbot using the prompt-based Bloom model. Our goal is to create a dataset of small...

module: chatbot

I am interested in creating a Conditional Random Field (CRF) model for natural language processing tasks in Rust. I believe that Rust's strong type system and performance benefits would make...

feature

Do you plan on creating keyword extraction for Vietnamese, I have tried RAKE, YAKE, KeyBert, TextRank, ... but the results are not promising.

feature

I know hyphenated names like "Jean-Luc Godard" are not typical in Vietnamese, but they may appear in texts, such as news articles. For `ner('Jean-Luc Godard', deep=True)` Expected: B-PER, I-PER, I-PER...

[Python 3.12 was released as a stable version 3.12.0](https://www.python.org/downloads/release/python-3120/) on 2023-10-03. This issue addresses adding support for the new version. Watch List - [x] [conda (osx-64)](https://repo.anaconda.com/pkgs/main/osx-64/) support `python-3.12.0` - [x]...

Hey! What a great project. Can you please update Rust bindings? There is no aarch64 image for `build_rust` An attempt to build https://github.com/undertheseanlp/underthesea/blob/d8d215943d0b39d525802429a7624b87be128991/extensions/docker/build-image/Dockerfile: ``` => ERROR [underthesea 6/27] RUN echo...