e-rara-ner

a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.

A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.

Anonymization of legal cases (Fr) based on Flair embeddings

Language Model Fine-tuning for Moby Dick

flairR: Bring Amazing Flair NLP to R

A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification

A small repository to test Captum Explainable AI with a trained Flair transformers-based text classifier.

Fair quantitative comparison of NLP embeddings from GloVe to RoBERTa with Sequential Bayesian Optimization fine-tuning using Flair and SentEval. Extension of HyperOpt library to log_b priors.

This repository adds examples on how to train Flair on Google Cloud Platform (GCP) AI Platform and how to deploy a Flair-model on GCP Cloud Run.