A machine learning classifier trained to categorise text about COVID-19 vaccines into 6 categories - Liberty or Freedom; Development, Provision and Access; Safety, Efficacy...

A machine learning classifier trained to categorise claims about COVID-19 into 10 categories proposed by the Reuters Institute for the Study of Journalism - Public authority...

Classifies short texts such as Wikipedia comments based on whether they contain toxic language

A service that tags abusive utterances in any text with the type of abuse (sexist, racist, etc.) and whether the abuse was aimed at the addressee or some other party. This can...

Service that processes threads of short texts such as tweets or forum postings and attempts to determine the stance (support, deny, question or comment) of each reply towards...

Service that processes threads of short English-language texts such as tweets or forum postings and attempts to determine the stance (support, deny, question or comment) of...

Classifies short texts such as Tweets based on whether they contain offensive language

Service that uses optical character recognition (OCR) to identify text contained within images. This is a multi-lingual service and not restricted to Latin scripts. It works...

Attempts to classify whether a text is hyper-partisan or not. This system won first prize in the Hyperpartisan News Detection task at SemEval 2019

Service that takes two news article texts and attempts to determine whether they refer to the same underlying news story. The articles may be in the same or in different...

https://github.com/HPAI-BSC/Focus-Metric Implementation of the Focus metric. This metric is able to evaluate explainability methods and quantify their coherency to the task...

A suite of methods for explainable AI for different Ai models

We provide a method to visualize the results of Boolean Matrix Factorization algorithms. Our method can also be used to visualize overlapping clusters in bipartite graphs. The...

GLocalX is a model-agnostic Local to Global explanation algorithm. Given a set of local explanations expressed in the form of decision rules, and a black-box model to explain,...

LASTS is a framework that can explain the decisions of black box models for time series classification. The explanation consists of factual and counterfactual rules revealing...

The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of...

MARLENA is novel technique able to explain the reasons behind any black-box multi-label classifier decision. It will generate an explanation in the form of a decision rule....

TRIPLEX is an explainability package for Transformer-based models fine-tuned on Natural Language Inference, Semantic Text Similarity, or Text Classification tasks. TRIPLEX...

Algorithms that tackle the problem of minimizing average/maximum hitting time (BMAH/BMMH) between different social network groups, given fixed shortcut edges. The...

Geolet is a Python library that offers an interpretable transformation and classification approach for trajectory data. Geolet first partitions trajectories into multiple...