Search Results for author: Peter Staar

Found 14 papers, 6 papers with code

ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents

no code implementations24 May 2023 Christoph Auer, Ahmed Nassar, Maksym Lysak, Michele Dolfi, Nikolaos Livathinos, Peter Staar

The results demonstrate substantial progress towards achieving robust and highly generalizing methods for document layout understanding.

Data Augmentation

Optimized Table Tokenization for Table Structure Recognition

no code implementations5 May 2023 Maksym Lysak, Ahmed Nassar, Nikolaos Livathinos, Christoph Auer, Peter Staar

The benefits of OTSL are that it reduces the number of tokens to 5 (HTML needs 28+) and shortens the sequence length to half of HTML on average.

Unsupervised Term Extraction for Highly Technical Domains

no code implementations24 Oct 2022 Francesco Fusco, Peter Staar, Diego Antognini

Developing term extractors that are able to generalize across very diverse and potentially highly technical domains is challenging, as annotations for domains requiring in-depth expertise are scarce and expensive to obtain.

Sentence Term Extraction

TableFormer: Table Structure Understanding with Transformers

1 code implementation CVPR 2022 Ahmed Nassar, Nikolaos Livathinos, Maksym Lysak, Peter Staar

In this way, we can obtain the content of the table-cells from programmatic PDF's directly from the PDF source and avoid the training of the custom OCR decoders.

Decoder object-detection +2

pNLP-Mixer: an Efficient all-MLP Architecture for Language

1 code implementation9 Feb 2022 Francesco Fusco, Damian Pascual, Peter Staar, Diego Antognini

Large pre-trained language models based on transformer architecture have drastically changed the natural language processing (NLP) landscape.

intent-classification Intent Classification +3

Unsupervised Domain Generalization by Learning a Bridge Across Domains

1 code implementation CVPR 2022 Sivan Harary, Eli Schwartz, Assaf Arbelle, Peter Staar, Shady Abu-Hussein, Elad Amrani, Roei Herzig, Amit Alfassy, Raja Giryes, Hilde Kuehne, Dina Katabi, Kate Saenko, Rogerio Feris, Leonid Karlinsky

The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system.

Domain Generalization Self-Supervised Learning

Robust PDF Document Conversion Using Recurrent Neural Networks

no code implementations18 Feb 2021 Nikolaos Livathinos, Cesar Berrospi, Maksym Lysak, Viktor Kuropiatnyk, Ahmed Nassar, Andre Carvalho, Michele Dolfi, Christoph Auer, Kasper Dinkla, Peter Staar

In this paper, we present a novel approach to document structure recovery in PDF using recurrent neural networks to process the low-level PDF data representation directly, instead of relying on a visual re-interpretation of the rendered PDF page, as has been proposed in previous literature.

Feature Engineering Information Retrieval +1

An Information Extraction and Knowledge Graph Platform for Accelerating Biochemical Discoveries

no code implementations19 Jul 2019 Matteo Manica, Christoph Auer, Valery Weber, Federico Zipoli, Michele Dolfi, Peter Staar, Teodoro Laino, Costas Bekas, Akihiro Fujita, Hiroki Toda, Shuichi Hirose, Yasumitsu Orii

Information extraction and data mining in biochemical literature is a daunting task that demands resource-intensive computation and appropriate means to scale knowledge ingestion.

Cannot find the paper you are looking for? You can Submit a new open access paper.