Machine learning models from Singapore's NLP research community

Last update: Dec 17, 2022

Related tags

Overview

SG-NLP

Machine learning models from Singapore's natural language processing (NLP) research community.

sgnlp is a Python package that allows you to easily get started on using various (NLP) models implemented using the Pytorch and Transfromers frameworks.

We have an accompanying demo site where you can interact with our models and get a better understanding on how they work.

Installation

Python >= 3.8

pip install sgnlp

Documentation

Visit our documentation for tutorials.

License

Code and models from this project are released under the MIT License unless otherwise stated. If a model's code is under a separate license, it can be found in the respective model's folder.

Comments

Change demo api to use gevent worker
Using multiple workers of the default type 'sync' in gunicorn is not working on Kubernetes

Workers constantly terminated due to signal 9

Try gevent to see if it works out
opened by jonheng 2
UFD use case tutorial and usability improvement
Added additional tutorial on how to use UFD to train and evaluate on custom dataset

Bug fix for UFD parse_args_and_load_config util function

Added feature to create folder if folder doesn't exist

Added some train args param in eval args param to improve usability

Made caching optional

Added validation to make debugging easier

Added links to config file examples for reccon models
opened by vincenttzc 1
Wrong assert comparison for SenticGCN dataclass
Latest SenticGCN implementation for the Dev branch. In the dataclass.py, post_init method in SenticGCNTrainArgs, there are the following assertions,

assert self.repeats > 1, "Repeats value must be at least 1." assert self.patience > 1, "Patience value must be at least 1."

The comparison operator should be >= instead.
bug
opened by raymondng76 0
47 centralized logging
Create a centralized logger for 'sgnlp' base logger

'sgnlp' logger is created from a config json and is init a the 'sgnlp' module init.py

Replace all logging method call with their own script specific logger
opened by raymondng76 0
Add parent class for preprocessor
[x] Create a module named sgnlp.base

[x] Add abstractmethods for preprocess, save, load

[x] Add batch iteration to parent __call__

[x] Parent __call__ should return a dictionary

enhancement
opened by jonheng 0
46 senticgcn bugfix
Add multi-word aspect support

Update documentation to reflect multi-word support

Update unit tests

Update usage example to include multi-word support
opened by raymondng76 0
Fix multi-word aspect issue with Sentic-GCN preprocessor

The current implementation of preprocessor matches a single aspect index for the purpose of matching postprocessor output. The aspect index field for process_input payload should be expended to handle aspects with multiple indexes.
bug

opened by raymondng76 0
Add Sentic-GCN demo_api to SGNlp
Close #43

This pull request is to add Sentic-GCN demo_api models to sgnlp. Includes the follow components:

model_card

api.py

dockerfiles

requirements.txt

usage.py
opened by K-WeiMing 0
Add Sentic-GCN to SGNlp
close #41

This pull request is to add Sentic-GCN models to sgnlp. Includes the follow components:

Models

Configs

Tokenizers

Embedding models

Trainer/Evaluator

Unit test

documentation

Does not include demo_api as it is covered in another issue tickets.
opened by raymondng76 0
download_pretrained for demo API does not cache downloaded files/models
To allow the containers to start up quicker, models and files were downloaded and cached during build time.

Recent changes in the huggingface transformers package has broken this functionality:

Released in v4.22.0

Issue

Possible choices moving forward:

Write a simple caching utility function

Stick to versions of transformers before 4.22.0
opened by jonheng 0
Add Stance Detection model

Paper: https://aclanthology.org/2020.emnlp-main.108.pdf

Prof: Jiang Jing from SMU

Repo: GitHub - jefferyYu/DualHierarchicalTransformer: Predicting Stance and Rumor Veracity via Dual Hierarchical Transformer

opened by atenzer 0

Releases(v0.4.0)

v0.4.0(Oct 7, 2022)

New model: Coherence Momentum Model
Source code(tar.gz)
Source code(zip)
v0.3.0(Apr 22, 2022)
New models:

Sentic GCN

LIF

UFD

Source code(tar.gz)
Source code(zip)
v0.2.0(Oct 19, 2021)
New models:

RST Pointer

GEC

Source code(tar.gz)
Source code(zip)
v0.1.1(Aug 26, 2021)

Bug fix on rumour detection module paths
Source code(tar.gz)
Source code(zip)
v0.1.0(Aug 26, 2021)

Removed UFD for further review.

Refactoring and improvements to LSR and Rumour detection models.
Source code(tar.gz)
Source code(zip)
v0.0.1(Aug 5, 2021)
Initial release of sgnlp.

Models included:

RECCON

LSR

UFD

Rumour detection twitter

Source code(tar.gz)
Source code(zip)

Owner

AI Singapore | AI Makerspace

Grow local AI talents and empowering start-ups, SMEs and enterprises with AI components, frameworks, platforms and advisory services.

GitHub Repository

A Persian Image Captioning model based on Vision Encoder Decoder Models of the transformers🤗.

Persian-Image-Captioning We fine-tuning the Vision Encoder Decoder Model for the task of image captioning on the coco-flickr-farsi dataset. The implem

15 Aug 25, 2022

Open source annotation tool for machine learning practitioners.

doccano doccano is an open source text annotation tool for humans. It provides annotation features for text classification, sequence labeling and sequ

7.1k Jan 01, 2023

Code from the paper "High-Performance Brain-to-Text Communication via Handwriting"

305 Dec 22, 2022

An algorithm that can solve the word puzzle Wordle with an optimal number of guesses on HARD mode.

WordleSolver An algorithm that can solve the word puzzle Wordle with an optimal number of guesses on HARD mode. How to use the program Copy this proje

3 Mar 02, 2022

Deep Learning for Natural Language Processing - Lectures 2021

This repository contains slides for the course "20-00-0947: Deep Learning for Natural Language Processing" (Technical University of Darmstadt, Summer term 2021).

0 Feb 21, 2022

This program do translate english words to portuguese

Python-Dictionary This program is used to translate english words to portuguese. Web-Scraping This program use BeautifulSoap to make web scraping, so

1 Oct 10, 2022

(ACL-IJCNLP 2021) Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models.

BERT Convolutions Code for the paper Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models. Contains expe

21 Jul 18, 2022

Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.

KB-NER: a Knowledge-based System for Multilingual Complex Named Entity Recognition The code is for the winner system (DAMO-NLP) of SemEval 2022 MultiC

116 Dec 27, 2022

Modeling cumulative cases of Covid-19 in the US during the Covid 19 Delta wave using Bayesian methods.

Introduction The goal of this analysis is to find a model that fits the observed cumulative cases of COVID-19 in the US, starting in Mid-July 2021 and

1 Jan 05, 2022

MEDIALpy: MEDIcal Abbreviations Lookup in Python

A small python package that allows the user to look up common medical abbreviations.

7 Nov 09, 2022

Neural network models for joint POS tagging and dependency parsing (CoNLL 2017-2018)

Neural Network Models for Joint POS Tagging and Dependency Parsing Implementations of joint models for POS tagging and dependency parsing, as describe

152 Sep 02, 2022

My Implementation for the paper EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks using Tensorflow

Easy Data Augmentation Implementation This repository contains my Implementation for the paper EDA: Easy Data Augmentation Techniques for Boosting Per

9 Oct 31, 2022

SEJE is a prototype for the paper Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering.

SEJE is a prototype for the paper Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering. Contents Inst

0 Oct 21, 2021

Officile code repository for "A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning"

CvarAdversarialRL Official code repository for "A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning". Initial setup Create a virtual

1 Nov 19, 2021

TFIDF-based QA system for AIO2 competition

AIO2 TF-IDF Baseline This is a very simple question answering system, which is developed as a lightweight baseline for AIO2 competition. In the traini

4 Feb 19, 2022

[ICLR 2021 Spotlight] Pytorch implementation for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."

RIDE: Long-tailed Recognition by Routing Diverse Distribution-Aware Experts. by Xudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu and Stella X. Yu at UC

205 Dec 16, 2022