Search Results for author:
Found 10 papers, 3 papers with code
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis
Lastly, we compare models trained on PubLayNet, DocBank and DocLayNet, showing that layout predictions of the DocLayNet-trained models are more robust and thus the preferred choice for general-purpose document-layout analysis.
Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness
In this paper, we focus on the case of document conversion to illustrate the particular challenges of scaling a complex data processing pipeline with a strong reliance on machine-learning methods on cloud infrastructure.
FETA: Towards Specializing Foundation Models for Expert Task Applications
However, as we show in this paper, FMs still have poor out-of-the-box performance on expert tasks (e. g. retrieval of car manuals technical illustrations from language queries), data for which is either unseen or belonging to a long-tail part of the data distribution of the huge datasets used for FM pre-training.
Ranked #1 on
Image-to-Text Retrieval
on FETA Car-Manuals
Corpus Conversion Service: A Machine Learning Platform to Ingest Documents at Scale
In this paper, we present a modular, cloud-based platform to ingest documents at scale.
Corpus Conversion Service: A machine learning platform to ingest documents at scale [Poster abstract]
We present a platform to ingest documents at scale which is powered by Machine Learning techniques and allows the user to train custom models on document collections.
An Information Extraction and Knowledge Graph Platform for Accelerating Biochemical Discoveries
Information extraction and data mining in biochemical literature is a daunting task that demands resource-intensive computation and appropriate means to scale knowledge ingestion.
Robust PDF Document Conversion Using Recurrent Neural Networks
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.
Optimized Table Tokenization for Table Structure Recognition
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.
ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents
The results demonstrate substantial progress towards achieving robust and highly generalizing methods for document layout understanding.
