Due to the advance of knowledge and technology, the fields of Artificial Intelligence (AI) and Machine Learning (ML) have grown in recent years leading to a significant increase of published papers. Since that, one of the new challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility is a necessary step to verify the reliability of research findings. Yet a 2016 survey revealed that more than 70% of researchers failed in their attempt to reproduce another researcher's experiments, and over 50% failed to reproduce one of their own experiments; a state of affairs that has been termed the ‘reproducibility crisis’ in science. The purpose of this work is to contribute to the field by reproducing the experiment and results achieved in the paper “Language Representation Models for Fine-Grained Sentiment Classification”, written by Cheang et al.

Due to the advance of knowledge and technology, the fields of Artificial Intelligence (AI) and Machine Learning (ML) have grown in recent years leading to a significant increase of published papers. Since that, one of the new challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility is a necessary step to verify the reliability of research findings. Yet a 2016 survey revealed that more than 70% of researchers failed in their attempt to reproduce another researcher's experiments, and over 50% failed to reproduce one of their own experiments; a state of affairs that has been termed the ‘reproducibility crisis’ in science. The purpose of this work is to contribute to the field by reproducing the experiment and results achieved in the paper “Language Representation Models for Fine-Grained Sentiment Classification”, written by Cheang et al.

Reproducibility in Natural Language Processing: A Case Study of Sentiment Classification

MINZONI, RICCARDO
2021/2022

Abstract

Due to the advance of knowledge and technology, the fields of Artificial Intelligence (AI) and Machine Learning (ML) have grown in recent years leading to a significant increase of published papers. Since that, one of the new challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility is a necessary step to verify the reliability of research findings. Yet a 2016 survey revealed that more than 70% of researchers failed in their attempt to reproduce another researcher's experiments, and over 50% failed to reproduce one of their own experiments; a state of affairs that has been termed the ‘reproducibility crisis’ in science. The purpose of this work is to contribute to the field by reproducing the experiment and results achieved in the paper “Language Representation Models for Fine-Grained Sentiment Classification”, written by Cheang et al.
2021
Reproducibility in Natural Language Processing: A Case Study of Sentiment Classification
Due to the advance of knowledge and technology, the fields of Artificial Intelligence (AI) and Machine Learning (ML) have grown in recent years leading to a significant increase of published papers. Since that, one of the new challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility is a necessary step to verify the reliability of research findings. Yet a 2016 survey revealed that more than 70% of researchers failed in their attempt to reproduce another researcher's experiments, and over 50% failed to reproduce one of their own experiments; a state of affairs that has been termed the ‘reproducibility crisis’ in science. The purpose of this work is to contribute to the field by reproducing the experiment and results achieved in the paper “Language Representation Models for Fine-Grained Sentiment Classification”, written by Cheang et al.
Reproducibility
NLP
Classification
File in questo prodotto:
File Dimensione Formato  
Minzoni_Riccardo.pdf

accesso riservato

Dimensione 3.6 MB
Formato Adobe PDF
3.6 MB Adobe PDF

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/42066