Pinned Repositories
FlagEmbedding
Retrieval and Retrieval-augmented LLMs
BIRB
IA_Tablut
A client that exploits machine learning in order to learn how to play Tablut.
Intermediate-linguistic-task-fine-tuning-on-Multilingual-models
The main goal of the thesis work was twofold, to shed light on the ongoing performances and quality issues of modern NLP approaches when applied to multi-language data scarce domains, and to propose an approach to mitigate such problems, trying to improve the results generated by the baseline models. The proposed approach, named Intermediate Task Training, consists in intro- ducing a supplementary training step in the training pipeline of models, by using tasks that are not strictly related to the target task.
IOT_SmartPot
Product-Recognition-on-Store-Shelves
Object detection in store shelves using SIFT along with Generalized Hough Transform and Meanshift Clustering Algorithm
RNN---La-divina-commedia
A Recurrent Neural Network trained to generate text using Dante Alighieri's style.
Simplex
SQuAD
Stanford Question Answering Dataset
Rispo997's Repositories
Rispo997/RNN---La-divina-commedia
A Recurrent Neural Network trained to generate text using Dante Alighieri's style.
Rispo997/Product-Recognition-on-Store-Shelves
Object detection in store shelves using SIFT along with Generalized Hough Transform and Meanshift Clustering Algorithm
Rispo997/BIRB
Rispo997/IA_Tablut
A client that exploits machine learning in order to learn how to play Tablut.
Rispo997/Intermediate-linguistic-task-fine-tuning-on-Multilingual-models
The main goal of the thesis work was twofold, to shed light on the ongoing performances and quality issues of modern NLP approaches when applied to multi-language data scarce domains, and to propose an approach to mitigate such problems, trying to improve the results generated by the baseline models. The proposed approach, named Intermediate Task Training, consists in intro- ducing a supplementary training step in the training pipeline of models, by using tasks that are not strictly related to the target task.
Rispo997/IOT_SmartPot
Rispo997/Simplex
Rispo997/SQuAD
Stanford Question Answering Dataset