Search Results for author:
Found 9 papers, 1 papers with code
Textual Data Augmentation for Efficient Active Learning on Tiny Datasets
In this paper we propose a novel data augmentation approach where guided outputs of a language generation model, e. g. GPT-2, when labeled, can improve the performance of text classifiers through an active learning process.
Enhancing Task-Specific Distillation in Small Data Regimes through Language Generation
To overcome this challenge, we present a novel approach where knowledge can be distilled from a teacher model to a student model through the generation of synthetic data.
A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots
Third, we define the methods used to embody personality in a CA, and review recent models using them.
Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages
For English, German and Urdu we use the existing RAVDESS, EMO-DB and URDU datasets.
A Deep CNN Architecture with Novel Pooling Layer Applied to Two Sudanese Arabic Sentiment Datasets
This SCM+MMA model is applied to SudSenti2 and SudSenti3 with accuracies of 92. 75% and 84. 39%.
Kinit Classification in Ethiopian Chants, Azmaris and Modern Music: A New Dataset and CNN Benchmark
In this paper, we create EMIR, the first-ever Music Information Retrieval dataset for Ethiopian music.
A New Amharic Speech Emotion Dataset and Classification Benchmark
This was done by training two VGGb SER models on ASED, one using Mel-spectrograms and the other using MFCC.
Using a Cross-Language Information Retrieval System based on OHSUMED to Evaluate the Moses and KantanMT Statistical Machine Translation Systems
The SMT systems were KantanMT, a cloud-based machine translation (MT) platform, and Moses, an open-source MT application.
Evaluating Machine Reading Systems through Comprehension Tests
The evaluation architecture is completely multilingual: test documents, questions, and their answers are identical in all the supported languages.
