Filip Gralinski

According to our database, Filip Gralinski authored at least 36 papers between 2003 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2024

Two Approaches to Diachronic Normalization of Polish Texts.

Kacper Dudzic, Filip Gralinski, Krzysztof Jassem, Marek Kubis, Piotr Wierzchon

CoRR, 2024

2023

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

Michal Turski, Tomasz Stanislawek, Karol Kaczmarek, Pawel Dyda, Filip Gralinski

Proceedings of the Document Analysis and Recognition - ICDAR 2023, 2023

Arxiv Tables: Document Understanding Challenge Linking Texts and Tables.

Karolina Konopka, Michal Turski, Filip Gralinski

Proceedings of the Document Analysis and Recognition - ICDAR 2023 Workshops, 2023

Modeling Spaced Repetition with LSTMs.

Jakub Pokrywka, Marcin Biedalak, Filip Gralinski, Krzysztof Biedalak

Proceedings of the 15th International Conference on Computer Supported Education, 2023

2022

Challenging America: Modeling language in longer time scales.

Jakub Pokrywka, Filip Gralinski, Krzysztof Jassem, Karol Kaczmarek, Krzysztof Jurkiewicz, Piotr Wierzchon

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Temporal Language Modeling for Short Text Document Classification with Transformers.

Jakub Pokrywka, Filip Gralinski

Proceedings of the 17th Conference on Computer Science and Intelligence Systems, 2022

Using Transformer models for gender attribution in Polish.

Karol Kaczmarek, Jakub Pokrywka, Filip Gralinski

Proceedings of the 17th Conference on Computer Science and Intelligence Systems, 2022

2021

Dynamic Boundary Time Warping for sub-sequence matching with few examples.

Lukasz Borchmann, Dawid Jurkiewicz, Filip Gralinski, Tomasz Górecki

Expert Syst. Appl., 2021

DUE: End-to-End Document Understanding Benchmark.

Lukasz Borchmann, Michal Pietruszka, Tomasz Stanislawek, Dawid Jurkiewicz, Michal Turski, Karolina Szyndler, Filip Gralinski

Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts.

Tomasz Stanislawek, Filip Gralinski, Anna Wróblewska, Dawid Lipinski, Agnieszka Kaliska, Paulina Rosalska, Bartosz Topolski, Przemyslaw Biecek

Proceedings of the 16th International Conference on Document Analysis and Recognition, 2021

LAMBERT: Layout-Aware Language Modeling for Information Extraction.

Lukasz Garncarek, Rafal Powalski, Tomasz Stanislawek, Bartosz Topolski, Piotr Halama, Michal Turski, Filip Gralinski

Proceedings of the 16th International Conference on Document Analysis and Recognition, 2021

Successive Halving Top-k Operator.

Michal Pietruszka, Lukasz Borchmann, Filip Gralinski

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Sparsifying Transformer Models with Differentiable Representation Pooling.

Michal Pietruszka, Lukasz Borchmann, Filip Gralinski

CoRR, 2020

On the Multi-Property Extraction and Beyond.

Tomasz Dwojak, Michal Pietruszka, Lukasz Borchmann, Filip Gralinski, Jakub Chledowski

CoRR, 2020

Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout.

Filip Gralinski, Tomasz Stanislawek, Anna Wróblewska, Dawid Lipinski, Agnieszka Kaliska, Paulina Rosalska, Bartosz Topolski, Przemyslaw Biecek

CoRR, 2020

LAMBERT: Layout-Aware language Modeling using BERT for information extraction.

Lukasz Garncarek, Rafal Powalski, Tomasz Stanislawek, Bartosz Topolski, Piotr Halama, Filip Gralinski

CoRR, 2020

ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them.

Dawid Jurkiewicz, Lukasz Borchmann, Izabela Kosmala, Filip Gralinski

Proceedings of the Fourteenth Workshop on Semantic Evaluation, 2020

Contract Discovery: Dataset and a Few-shot Semantic Retrieval Challenge with Competitive Baselines.

Lukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Lukasz Szalkiewicz, Gabriela Palka, Karol Kaczmarek, Agnieszka Kaliska, Filip Gralinski

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

From Dataset Recycling to Multi-Property Extraction and Beyond.

Tomasz Dwojak, Michal Pietruszka, Lukasz Borchmann, Jakub Chledowski, Filip Gralinski

Proceedings of the 24th Conference on Computational Natural Language Learning, 2020

2019

Searching for Legal Clauses by Analogy. Few-shot Semantic Retrieval Shared Task.

Lukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Lukasz Szalkiewicz, Gabriela Palka, Karol Kaczmarek, Agnieszka Kaliska, Filip Gralinski

CoRR, 2019

GEval: Tool for Debugging NLP Datasets and Models.

Filip Gralinski, Anna Wróblewska, Tomasz Stanislawek, Kamil Grabowski, Tomasz Górecki

Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2019

2017

Automated Normalization and Analysis of Historical Texts.

Pawel Skórzewski, Krzysztof Jassem, Filip Gralinski

Proceedings of the Human Language Technology. Challenges for Computer Science and Linguistics, 2017

The RetroC challenge: how to guess the publication year of a text?

Filip Gralinski, Rafal Jaworski, Lukasz Borchmann, Piotr Wierzchon

Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage, 2017

2016

Vive la Petite Différence! - Exploiting Small Differences for Gender Attribution of Short Texts.

Filip Gralinski, Rafal Jaworski, Lukasz Borchmann, Piotr Wierzchon

Proceedings of the Text, Speech, and Dialogue - 19th International Conference, 2016

"He Said She Said" ― a Male/Female Corpus of Polish.

Filip Gralinski, Lukasz Borchmann, Piotr Wierzchon

Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016, 2016

2015

RetroC - A Corpus for Evaluating Temporal Classifiers.

Filip Gralinski, Piotr Wierzchon

Proceedings of the Human Language Technology. Challenges for Computer Science and Linguistics, 2015

2013

PSI-Toolkit: A Natural Language Processing Pipeline.

Filip Gralinski, Krzysztof Jassem, Marcin Junczys-Dowmunt

Proceedings of the Computational Linguistics - Applications, 2013

2012

Mining the Web for Idiomatic Expressions Using Metalinguistic Markers.

Filip Gralinski

Proceedings of the Text, Speech and Dialogue - 15th International Conference, 2012

2010

Computational Lexicography of Multi-Word Units. How Efficient Can It Be?

Filip Gralinski, Agata Savary, Monika Czerepowicka, Filip Makowiecki

Proceedings of the 2010 Workshop on Multiword Expressions: from Theory to Applications, 2010

Matura Evaluation Experiment Based on Human Evaluation of Machine Translation.

Aleksandra Wojak, Filip Gralinski

Proceedings of the International Multiconference on Computer Science and Information Technology, 2010

Mining Parenthetical Translations for Polish-English Lexica.

Filip Gralinski

Proceedings of the Computational Linguistics and Intelligent Text Processing, 2010

2009

Acquiring Bilingual Lexica from Keyword Listings.

Filip Gralinski, Krzysztof Jassem, Roman Kurc

Proceedings of the Human Language Technology. Challenges for Computer Science and Linguistics, 2009

Looking for new words out there.

Filip Gralinski, Marcin Walas

Proceedings of the International Multiconference on Computer Science and Information Technology, 2009

An Environment for Named Entity Recognition and Translation.

Filip Gralinski, Krzysztof Jassem, Michal Marcinczuk

Proceedings of the 13th Annual conference of the European Association for Machine Translation, 2009

2006

Some Methods of Describing Discontinuity in Polish and Their Cost-Effectiveness.

Filip Gralinski

Proceedings of the Text, Speech and Dialogue, 9th International Conference, 2006

2003

Applying Transition Networks in Translating Polish E-Mails.

Krzysztof Jassem, Filip Gralinski, Tomasz Kowalski

Proceedings of the Intelligent Information Processing and Web Mining, 2003