activity
20192025
collaborators

9 papers

cs.LG2025

Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation

Patryk Bartkowiak, Filip Graliński

Transformer-based models have demonstrated significant success in various source code representation tasks. Nonetheless, traditional positional embeddings employed by these models…

cs.LG2024

Tackling prediction tasks in relational databases with LLMs

Marek Wydmuch, Łukasz Borchmann, Filip Graliński

Though large language models (LLMs) have demonstrated exceptional performance across numerous problems, their application to predictive tasks in relational databases remains largel…

cs.CL2023

CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data

Michał Turski, Tomasz Stanisławek, Karol Kaczmarek +2

In recent years, the field of document understanding has progressed a lot. A significant part of this progress has been possible thanks to the use of language models pretrained on…

cs.CL2020

From Dataset Recycling to Multi-Property Extraction and Beyond

Tomasz Dwojak, Michał Pietruszka, Łukasz Borchmann +2

This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outper…

cs.LG2020

Successive Halving Top-k Operator

Michał Pietruszka, Łukasz Borchmann, Filip Graliński

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…

cs.CL2020

On the Multi-Property Extraction and Beyond

Tomasz Dwojak, Michał Pietruszka, Łukasz Borchmann +2

In this paper, we investigate the Dual-source Transformer architecture on the WikiReading information extraction and machine reading comprehension dataset. The proposed model outpe…