newsClassifier_v1

Model Card for raicrits/newsClassifier_v1

<!-- Provide a quick summary of what the model is/does. -->

This model analyses the input text and provides the class the text belongs to among the follofing ones:

0"sport"

1"giustizia-criminalita-sicurezza"

2"editoria-stampa-mass_media"

3"lavoro-previdenza"

4"trasporti"

5"cultura-scienze_umane"

6"esteri"

7"istruzione-formazione"

8"industria-impresa-produzione"

9"vita_e_cultura_religiosa"

10"sanita-salute"

11"economia-credito-finanza"

12"musica_e_spettacolo"

13"cronaca"

14"ambiente-natura-territorio"

15"politica-partiti-istituzioni-sindacati"

16"avvenimenti-celebrazioni-eventi_storici"

17"consumi-servizi"

18"individuo-famiglia-associazioni-societa"

19"commercio"

20"scienze-tecnologie"

21"pubblica_amministrazione-enti_locali"

22"tempo_libero"

23"arte-artigianato"

24"usi_e_costumi"

25"beni_culturali"

26"agricoltura-zootecnia"

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Alberto Messina ([email protected])
• Model type: BERT for Sequence Classification
• Language(s) (NLP): Italian
• License: TBD
• Finetuned from model: https://huggingface.co/xlm-roberta-base

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: N/A
• Paper [optional]: N/A
• Demo [optional]: N/A

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

The model should be used giving a short paragraph of text in Italian as input about which it is requested to get the most probable class.

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

TBA

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

The model should not be used as a general purpose classifier, i.e. on text which is not originated from news programme transcription or siilar content.

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

The training dataset is made up of automatic transcriptions from RAI Italian newscasts, therefore there is an intrinsic bias in the kind of topics included in the dataset.

How to Get Started with the Model

Use the code below to get started with the model.

TBA

Training Details

Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

TBA

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

TBA

Training Hyperparameters

• Training regime: Mixed Precision

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

TBA

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Data Card if possible. -->

TBA

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

TBA

Results

TBA

Summary

TBA

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: 2 NVIDIA A100/40Gb
• Hours used: 2
• Cloud Provider: Private Infrastructure
• Carbon Emitted: 0.22 kg CO2 eq.

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

TBA

More Information [optional]

TBA

Model Card Authors [optional]

Alberto Messina

Model Card Contact

[email protected]