Jakub Náplava

Orcid: 0000-0003-2259-1377

According to our database1, Jakub Náplava authored at least 11 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking.
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024

Some Like It Small: Czech Semantic Embedding Models for Industry Applications.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2022
Czech Grammar Error Correction with a Large and Diverse Corpus.
Trans. Assoc. Comput. Linguistics, 2022

Siamese BERT-Based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Diacritics Restoration using BERT with Analysis on Czech language.
Prague Bull. Math. Linguistics, 2021

RobeCzech: Czech RoBERTa, a Monolingual Contextualized Language Representation Model.
Proceedings of the Text, Speech, and Dialogue - 24th International Conference, 2021

Character Transformations for Non-Autoregressive GEC Tagging.
Proceedings of the Seventh Workshop on Noisy User-generated Text, 2021

Understanding Model Robustness to User-generated Noisy Texts.
Proceedings of the Seventh Workshop on Noisy User-generated Text, 2021

2019
CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction.
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, 2019

Grammatical Error Correction in Low-Resource Scenarios.
Proceedings of the 5th Workshop on Noisy User-generated Text, 2019

2018
Diacritics Restoration Using Neural Networks.
Proceedings of the Eleventh International Conference on Language Resources and Evaluation, 2018


  Loading...