Employing Wikipedia as a resource for Named Entity Recognition in Morphologically complex under-resourced languages

no code implementations • RANLP (BUCC) 2021 • Aravind Krishnan, Stefan Ziehe, Franziska Pannach, Caroline Sporleder

We propose a novel approach for rapid prototyping of named entity recognisers through the development of semi-automatically annotated datasets.

named-entity-recognition Named Entity Recognition +1

GCDH@LT-EDI-EACL2021: XLM-RoBERTa for Hope Speech Detection in English, Malayalam, and Tamil

no code implementations • EACL (LTEDI) 2021 • Stefan Ziehe, Franziska Pannach, Aravind Krishnan

This paper describes approaches to identify Hope Speech in short, informal texts in English, Malayalam and Tamil using different machine learning techniques.

BIG-bench Machine Learning Cross-Lingual Transfer +2

On the N-gram Approximation of Pre-trained Language Models

no code implementations • 12 Jun 2023 • Aravind Krishnan, Jesujoba Alabi, Dietrich Klakow

This study investigates the potential usage of PLMs for language modelling in ASR.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Exploring shared memory architectures for end-to-end gigapixel deep learning

no code implementations • 24 Apr 2023 • Lucas W. Remedios, Leon Y. Cai, Samuel W. Remedios, Karthik Ramadass, Aravind Krishnan, Ruining Deng, Can Cui, Shunxing Bao, Lori A. Coburn, Yuankai Huo, Bennett A. Landman

The M1 Ultra SoC was able to train the model directly on gigapixel images (16000$\times$64000 pixels, 1. 024 billion pixels) with a batch size of 1 using over 100 GB of unified memory for the process at an average speed of 1 minute and 21 seconds per batch with Tensorflow 2/Keras.

whole slide images