Search Results for author: Dimitra Vergyri

Found 3 papers, 0 papers with code

Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning

no code implementations16 Oct 2023 Anirudh Som, Karan Sikka, Helen Gent, Ajay Divakaran, Andreas Kathol, Dimitra Vergyri

Paraphrasing of offensive content is a better alternative to content removal and helps improve civility in a communication environment.

In-Context Learning

Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules

no code implementations17 Sep 2020 Edgar Altszyler, Pablo Brusco, Nikoletta Basiou, John Byrnes, Dimitra Vergyri

In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data.

Descriptive dialog state tracking

Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition

no code implementations16 Feb 2018 Vikramjit Mitra, Wen Wang, Chris Bartels, Horacio Franco, Dimitra Vergyri

This paper explores the use of multi-view features and their discriminative transforms in a convolutional deep neural network (CNN) architecture for a continuous large vocabulary speech recognition task.

speech-recognition Speech Recognition

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