[PDF][PDF] Overview of the evalita 2016 named entity recognition and linking in italian tweets (neel-it) task

P Basile, A Caputo, AL Gentile, G Rizzo - of the Final Workshop, 2016 - publicatt.unicatt.it
This report describes the main outcomes of the 2016 Named Entity rEcognition and Linking
in Italian Tweet (NEEL-IT) Challenge. The goal of the challenge is to provide a benchmark …

Which matters most? comparing the impact of concept and document relationships in topic models

S Terragni, D Nozza, E Fersini… - Proceedings of the First …, 2020 - aclanthology.org
Topic models have been widely used to discover hidden topics in a collection of documents.
In this paper, we propose to investigate the role of two different types of relational …

Word embeddings for unsupervised named entity linking

D Nozza, C Sas, E Fersini, E Messina - … 28–30, 2019, Proceedings, Part II …, 2019 - Springer
The huge amount of textual user-generated content on the Web has incredibly grown in the
last decade, creating new relevant opportunities for different real-world applications and …

Что имеет большее значение? Сравнение влияния концептуальных и документальных отношений в тематических моделях

С ТЕРРАНЬИ, Э ФЕРСИНИ, Э МЕССИНА… - Международный …, 2021 - elibrary.ru
Тематические модели широко используются для обнаружения скрытых тем в
коллекциях документов. В статье предполагается изучить роль двух разных типов …

Deep Learning for Feature Representation in Natural Language Processing

D Nozza - 2018 - boa.unimib.it
The huge amount of textual user-generated content on the Web has incredibly grown in the
last decade, creating new relevant opportunities for different real-world applications and …