Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Pietruszka, Michał"'
Autor:
Borchmann, Łukasz, Pietruszka, Michał, Jaśkowski, Wojciech, Jurkiewicz, Dawid, Halama, Piotr, Józiak, Paweł, Garncarek, Łukasz, Liskowski, Paweł, Szyndler, Karolina, Gretkowski, Andrzej, Ołtusek, Julita, Nowakowska, Gabriela, Zawłocki, Artur, Duhr, Łukasz, Dyda, Paweł, Turski, Michał
The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed
Externí odkaz:
http://arxiv.org/abs/2408.04632
Autor:
Van Landeghem, Jordy, Tito, Rubén, Borchmann, Łukasz, Pietruszka, Michał, Józiak, Paweł, Powalski, Rafał, Jurkiewicz, Dawid, Coustaty, Mickaël, Ackaert, Bertrand, Valveny, Ernest, Blaschko, Matthew, Moens, Sien, Stanisławek, Tomasz
We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research p
Externí odkaz:
http://arxiv.org/abs/2305.08455
Autor:
Pietruszka, Michał, Turski, Michał, Borchmann, Łukasz, Dwojak, Tomasz, Pałka, Gabriela, Szyndler, Karolina, Jurkiewicz, Dawid, Garncarek, Łukasz
The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Following this constatation, we propose a framework for text-to-table neu
Externí odkaz:
http://arxiv.org/abs/2206.04045
Autor:
Powalski, Rafał, Borchmann, Łukasz, Jurkiewicz, Dawid, Dwojak, Tomasz, Pietruszka, Michał, Pałka, Gabriela
We address the challenging problem of Natural Language Comprehension beyond plain-text documents by introducing the TILT neural network architecture which simultaneously learns layout information, visual features, and textual semantics. Contrary to p
Externí odkaz:
http://arxiv.org/abs/2102.09550
This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we introdu
Externí odkaz:
http://arxiv.org/abs/2011.03228
We propose a differentiable successive halving method of relaxing the top-k operator, rendering gradient-based optimization possible. The need to perform softmax iteratively on the entire vector of scores is avoided by using a tournament-style select
Externí odkaz:
http://arxiv.org/abs/2010.15552
We propose a novel method to sparsify attention in the Transformer model by learning to select the most-informative token representations during the training process, thus focusing on the task-specific parts of an input. A reduction of quadratic time
Externí odkaz:
http://arxiv.org/abs/2009.05169
In this paper, we investigate the Dual-source Transformer architecture on the WikiReading information extraction and machine reading comprehension dataset. The proposed model outperforms the current state-of-the-art by a large margin. Next, we introd
Externí odkaz:
http://arxiv.org/abs/2006.08281
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Heat Transfer Engineering; 2023, Vol. 44 Issue 11/12, p1015-1024, 10p