AI in Production

Home
Archive
About
Generative (TrOCR) models calibration
Teaching a generative TrOCR model to know what it doesn't know
 • 
Tin Ferković

November 2023

LinguaAI: AI-Powered Personalized Conversations for Comprehensive Language Learning
Beyond Traditional Learning: The GPT-4 Edge in Adaptive Language Tutoring for any Language and any Level.
 • 
Mihaela Bakšić

August 2023

Multi-Task Learning with Intermediate Continual Learning for Industry NLP Use Cases
Utilizing adapters and hypernetworks to efficiently, effectively, and continuously train multiple tasks
 • 
Tin Ferković
Exploring State-of-the-Art Models for Document-Level Entity Relation Extraction
Document-level entity relation extraction involves identifying and categorizing relationships between entities mentioned within whole documents, rather…
 • 
Dunja Smigovec

July 2023

May 2023

Data Extraction from Invoice Type Documents using Large Language Models
Towards tailored made AI models that adapt to changes and match the needs and demands of a dynamic real-world environment.
 • 
Mihaela Kakarigi
 and 
Zeljko

January 2023

Annotation Team Lead and Teamwork
Document annotation is a crucial step in training AI models, particularly in the context of Natural Language Processing (NLP). It involves adding labels…
 • 
Dragan Kraljević
Named Entity Recognition Using a Pre-Trained LayoutLMv2 Model
The amount of data generated by humans is ever-increasing, much of which is stored in documents and forms that need to be analyzed to extract relevant…
 • 
Marko Cvjetko
Named Entity Recognition using BERT on Subsampled Datasets
The Named-Entity Recognition (NER) system I worked on during my internship at doXray is part of a live production system. At doXray, models in…
 • 
Eva Jagodić
 and 
Bruno Šarlija
© 2024 doXray
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture