Author: Deep Learner

Text

Saliency-based Span Mixup for Text Classification

SSMix Saliency-based Span Mixup for Text Classification (Findings of ACL 2021) Abstract Data augmentation with mixup has shown to be effective on various computer vision tasks. Despite its great success, there has been a hurdle to apply mixup to NLP tasks since text consists of discrete tokens with variable length. In this work, we propose SSMix, a novel mixup method where the operation is performed on input text rather than on hidden vectors like previous approaches. SSMix synthesizes a sentence […]

Read more
Framework

Framework that uses artificial intelligence applied to mathematical models to make predictions

LiconIA Framework that uses artificial intelligence applied to mathematical models to make predictions Requirements Python 3.6 or superior (sudo apt-get install python3.6 under Linux)Python virtual environment (sudo apt-get install python3.6-venv under Linux) Development and Tests Installing the package Start by creating a new virtual environment for your project. Next, update the packages pip and setuptools to the latest version. Then install the package itself. $ sudo apt-get install python3-tk $ /usr/bin/python3.6 -m venv –prompt=”LiconIA” venv $ source venv/bin/activate (LiconIA) $ […]

Read more
Command-line Tools

A simple tool to query the awesome ippsec.rocks website from terminal

ippsec-cli This a simple tool to query the awesome ippsec.rocks website from your terminal Installation and usage cd /opt git clone https://github.com/stark0de/ippsec-cli cd ippsec-cli pip3 install -r requirements.txt chmod +x ippsec-cli.py python3 -W ignore ippsec-cli.py Note: optionally you can go to /home/$USER/.bashrc and add this line so u can just launch it putting ippsec-cli in your terminal: vim /home/$USER/.bashrc alias ippsec-cli=”python3 -W ignore /opt/ippsec-cli/ippsec-cli.py” source /home/$USER/.bashrc Credits to @HexF_me, @Shell_ock and of course to the awesome Ippsec 😉 Note: I’ve […]

Read more
Machine Learning

A topological message passing system for solid models

BRepNet A topological message passing system for solid models This repository contains the an implementation of BRepNet: A topological message passing system for solid models. About BRepNet BRepNet is a neural network specifically designed to operate on solid models. It uses additional topological information present in the boundary representation (B-Rep) data structure to perform convolutions in a way which is not possible for arbitrary graphs. As B-Reps describe manifolds, they contain additional topological information which includes the ordering of edges […]

Read more
Network

A Network Shredder IDS for python

Network-Shredder Network-Shredder is a python based NIDS. Installation git clone https://github.com/v0lck3r/Network-Shredder.git cd Network-Shredder pip3 install -r requirements.txt Example usage python3 Network-Shredder.py -h Live mode python3 Network-Shredder.py rules.txt –interface tun0 Start web application python3 Network-Shredder.py rules.txt –interface tun0 –web Console quiet mode python3 Network-Shredder.py rules.txt –interface tun0 –web –quiet Specify log directory python3 Network-Shredder.py rules.txt –logdir /tmp/ –interface tun0 –web Pcap based detection python3 Network-Shredder.py rules.txt –pcap pcap_file.pcap GitHub https://github.com/v0lck3r/Network-Shredder    

Read more
Text

Print text color and text format on Term with Python

term-printer Print ‘text color’ and ‘text format’ on Term with Python ※ It may not work depending on the OS and shell used. PIP $ pip install term-printer import from term_printer import Color, Color256, ColorRGB, StdText, cprint If you want to override bultin print function from term_printer import Color, Color256, ColorRGB, StdText, cprint as print Usage 1. Attrs print Applies to all characters. You can specify Format, Color, Color256, and ColorRGB. Able to specify more than one. source from term_printer […]

Read more
Machine Learning

Dependency Cluster Attention for Aspect-level sentiment classification

DLCF-DCA codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification. submitted to 《Neurocomputing》. Requirement Python >= 3.6 PyTorch >= 1.0 pytorch-transformers == 1.2.0 SpaCy >= 2.2 To use our models, you need download en_core_web_sm by python -m spacy download en_core_web_sm Training python train.py –model dlcf_dca Model Architecture Note Some important scripts to note: datasets/semeval14/*.seg: Preprocessed training and testing sentences in SemEval2014. datasets/semeval15/*.seg: Preprocessed training and testing sentences in SemEval2015. datasets/semeval16/*.seg: Preprocessed training and […]

Read more
Neural Network

Neural G2P to portuguese language with python

neural-g2p-portuguese Grapheme-to-phoneme (G2P) conversion is the process of generating pronunciation for words based on their written form. It has a highly essential role for natural language processing, text-to-speech synthesis and automatic speech recognition systems. This project was adapted from https://github.com/hajix/G2P. Dependencies The following libraries are used:pytorchtqdmmatplotlib Install dependencies using pip: pip3 install -r requirements.txt Dataset The dataset used here was taken from site http://www.portaldalinguaportuguesa.org/, as well as some insertions made by me so that the dataset would give more coverage […]

Read more
Text-to-Speech

Attention Based Grapheme To Phoneme with python

G2P The G2P algorithm is used to generate the most probable pronunciation for a word not contained in the lexicon dictionary. It could be used as a preprocess of text-to-speech system to generate pronunciation for OOV words. Dependencies The following libraries are used:pytorchtqdmmatplotlib Install dependencies using pip: pip3 install -r requirements.txt Dataset Currently the following languages are supported: EN: English FA: Farsi RU: Russian You could easily provide and use your own language specific pronunciatin doctionary for training G2P. More […]

Read more
Beginner, Data Science, NLP, Python, Text, Word Embeddings

Part 8: Step by Step Guide to Master NLP – Useful Natural Language Processing Tasks

This article was published as a part of the Data Science Blogathon Introduction This article is part of an ongoing blog series on Natural Language Processing (NLP). Up to part-7 of this series, we completed the most useful concepts in NLP. While going away in this series, let’s first discuss some of the useful tasks of NLP so that you have much clarity about what you can do by learning the NLP. After this part, we will start our discussion on […]

Read more
1 … 643 644 645 646 647 … 984