Artificial Intelligence in higher education opens new possibilities for improving the lecturing process, such as enriching didactic materials, helping in assessing students' works or even providing directions to the teachers on how to enhance the lectures.
Named entities recognition (NER) and disambiguation (NED) can add semantic context to the recognized named entities in texts.
We introduce a new loss function TripleEntropy, to improve classification performance for fine-tuning general knowledge pre-trained language models based on cross-entropy and SoftTriple loss.
Contrary to existing recommendation systems, our platform supports multiple types of interaction data with multiple modalities of metadata natively.
As a result, fashion retrieval is an active field of research both in academia and the industry.
Ranked #1 on Image Retrieval on Exact Street2Shop
Datasets that boosted state-of-the-art solutions for Question Answering (QA) systems prove that it is possible to ask questions in natural language manner.
In this paper we present the results of an investigation of the importance of verbs in a deep learning QA system trained on SQuAD dataset.