Ozge Sevgili
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ozge Sevgili has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Panchenko
Skolkovo Institute of Science and Technology, Moscow, Russia
2 shared publications - Abhik Jana
Computer Science Engineering IIT Kharagpur India
1 shared publication - Artem Shelmanov
ISP RAS Research Center for Trusted Artificial Intelligence
1 shared publication - Chris Biemann
Department of Informatics Language Technology Group Universität Hamburg Germany
1 shared publication - Chris Biemann
University of Hamburg
1 shared publication - Mikhail Arkhipov
Neural Networks and Deep Learning Laboratory Moscow Institute of Physics and Technology 9 Institutskiy per. 141701 Dolgoprudny Moscow Russia
1 shared publication
Latest Publications
- 12 March 2024
- Published by Springer Nature
- p. 126-140
Unsupervised Ultra-Fine Entity Typing with Distributionally Induced Word Senses
- 12 March 2024
- Published by Springer Nature
- p. 126-140
Unsupervised Ultra-Fine Entity Typing with Distributionally Induced Word Senses
- Open Access
Neural Entity Linking: A Survey of Models Based on Deep Learning
This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing. Its goal is to systemize design features of neural entity linking systems and compare their performance to the remarkable classic methods on common benchmarks. This work distills a generic architecture of a neural EL system and discusses its components, such as candidate generation, mention-context encoding, and entity ranking, summarizing prominent methods for each of them. The vast variety of modifications of this general architecture are grouped by several common themes: joint entity mention detection and disambiguation, models for global linking, domain-independent techniques including zero-shot and distant supervision methods, and cross-lingual approaches. Since many neural models take advantage of entity and mention/context embeddings to represent their meaning, this work also overviews prominent entity embedding techniques. Finally, the survey touches on applications of entity linking, focusing on the recently emerged use-case of enhancing deep pre-trained masked language models based on the Transformer architecture.
Open AccessNeural Entity Linking: A Survey of Models Based on Deep Learning
This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing. Its goal is to systemize design features of neural entity linking systems and compare their performance to the remarkable classic methods on common benchmarks. This work distills a generic architecture of a neural EL system and discusses its components, such as candidate generation, mention-context encoding, and entity ranking, summarizing prominent methods for each of them. The vast variety of modifications of this general architecture are grouped by several common themes: joint entity mention detection and disambiguation, models for global linking, domain-independent techniques including zero-shot and distant supervision methods, and cross-lingual approaches. Since many neural models take advantage of entity and mention/context embeddings to represent their meaning, this work also overviews prominent entity embedding techniques. Finally, the survey touches on applications of entity linking, focusing on the recently emerged use-case of enhancing deep pre-trained masked language models based on the Transformer architecture.