Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tomasz Dwojak

Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer


Mar 02, 2021
Rafał Powalski, Łukasz Borchmann, Dawid Jurkiewicz, Tomasz Dwojak, Michał Pietruszka, Gabriela Pałka

* Improved results on RVL-CDIP, integrated abstract and main text, clarifications 

  Access Paper or Ask Questions

From Dataset Recycling to Multi-Property Extraction and Beyond


Nov 06, 2020
Tomasz Dwojak, Michał Pietruszka, Łukasz Borchmann, Jakub Chłędowski, Filip Graliński

* Accepted at CoNLL 2020; this article supersedes arXiv: 2006.08281 

  Access Paper or Ask Questions

On the Multi-Property Extraction and Beyond


Jun 15, 2020
Tomasz Dwojak, Michał Pietruszka, Łukasz Borchmann, Filip Graliński, Jakub Chłędowski

* 5 pages 

  Access Paper or Ask Questions

Fast Neural Machine Translation Implementation


Jun 07, 2018
Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, Kenneth Heafield


  Access Paper or Ask Questions

Marian: Fast Neural Machine Translation in C++


Apr 04, 2018
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, Andr├ę F. T. Martins, Alexandra Birch

* Demonstration paper 

  Access Paper or Ask Questions

Predicting Target Language CCG Supertags Improves Neural Machine Translation


Jul 18, 2017
Maria Nadejde, Siva Reddy, Rico Sennrich, Tomasz Dwojak, Marcin Junczys-Dowmunt, Philipp Koehn, Alexandra Birch

* Accepted at the Second Conference on Machine Translation (WMT17). This version includes more results regarding target syntax for Romanian->English and reports fewer results regarding source syntax 

  Access Paper or Ask Questions

Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions


Nov 30, 2016
Marcin Junczys-Dowmunt, Tomasz Dwojak, Hieu Hoang

* Accepted for presentation at IWSLT 2016, Seattle 

  Access Paper or Ask Questions

The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT


Jun 23, 2016
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich


  Access Paper or Ask Questions