Search Results for author: Marcin Pietron

Found 7 papers, 1 papers with code

Efficient argument classification with compact language models and ChatGPT-4 refinements

no code implementations20 Mar 2024 Marcin Pietron, Rafał Olszowski, Jakub Gomułka

Argument mining (AM) is defined as the task of automatically identifying and extracting argumentative components (e. g. premises, claims, etc.)

Argument Mining

Context based lemmatizer for Polish language

no code implementations23 Jul 2022 Michal Karwatowski, Marcin Pietron

In computational linguistics, lemmatisation is the algorithmic process of determining the lemma of a word based on its intended meaning.

LEMMA Lemmatization +1

Retrain or not retrain? -- efficient pruning methods of deep CNN networks

no code implementations12 Feb 2020 Marcin Pietron, Maciej Wielgosz

Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation.

Image Classification object-detection +2

Method for Hybrid Precision Convolutional Neural Network Representation

no code implementations24 Jul 2018 Mo'taz Al-Hami, Marcin Pietron, Rishi Kumar, Raul A. Casas, Samer L. Hijazi, Chris Rowen

This invention addresses fixed-point representations of convolutional neural networks (CNN) in integrated circuits.

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