175 citations · 199 across the 9 of their papers we have counts for
5 papers · 1 filter
ProtagonistTagger -- a Tool for Entity Linkage of Persons in Texts from Various Languages and Domains
Weronika Lajewska, Anna Wroblewska
Named entities recognition (NER) and disambiguation (NED) can add semantic context to the recognized named entities in texts. Named entity linkage in texts, regardless of a domain,…
Applying SoftTriple Loss for Supervised Language Model Fine Tuning
Witold Sosnowski, Anna Wroblewska, Piotr Gawrysiak
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 SoftT…
Named Entity Recognition -- Is there a glass ceiling?
Tomasz Stanislawek, Anna Wróblewska, Alicja Wójcicka +2
Recent developments in Named Entity Recognition (NER) have resulted in better and better models. However, is there a glass ceiling? Do we know which types of errors are still hard…
Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System
Barbara Rychalska, Dominika Basaj, Przemyslaw Biecek +1
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. We show that main verbs in questions carr…
How much should you ask? On the question structure in QA systems
Dominika Basaj, Barbara Rychalska, Przemyslaw Biecek +1
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. However, users are still…