In the wild extraction of entities that are found using Flair and displayed using a very elegant front-end.

Code and data for paper 'Causality extraction based on self-attentive BiLSTM-CRF with transferred embeddings'

📜 Dehyphenation of broken text (mainly German), i.e., extracted from a PDF

Text2Emoji helps you add necessary emojis to your text by analysing the emotion behind the writing.

Container-first, JSON-configurable, NLP REST service based on Flair

Large Scale benchmarking of state of the art text vectorizers

ANTILLES : An Open French Linguistically Enriched Part-of-Speech Corpus

Use of State of the Art FLAIR library for the NLP datasets

FewClick-TrainAndHost is a platform to auto train a text classification model and later convert it to a flask based web-app in just few clicks.

NLP related concepts, challenges and datasets

📑Semantic content similarity search experiment on heartfulness.org mission literature dataset. Developed using pytorch and azure machine learning service.

A deep learning approach for detecting sarcasm in Headlines

pretrained transformer and embeddings language models

Bengali flair based model collection

An overview of the possibilities of using TARS models for low language resources

My code and research while exploring NLP fake news detection under an internship.

A StackExchange flair react component

This repository contains my scripts, results and visualization for my bachelor thesis "Medical concept PROBLEM: Polarity, Modality and Temporal Relations" - ON GOING, doing some code reorganize

A multi-lingual named entity classifier to perform named entity recognition (NER) on two datasets, International: CoNLL 2003, Chinese: Weibo. We used the current state-of-the-art model to test on CoNLL++ dataset, achieved a F1-score of 94.3% with pooled-embeddings.