Identifying the author of some verses

Problem Description

A dataset with poems in Romanian is provided, each written by one of 7 authors. The poems have been subsequently divided into groups of 4 verses.

The 7 authors are:

• Ana Blandiana
• George Bacovia
• George Toparceanu
• Grigore Vieru
• Lucian Blaga
• Mihai Eminescu
• Vasile Alecsandri

A group of 4 verses can represent:

• A complete stanza (quatrain)
• A part of a larger stanza (5, 6, 7 verses, etc.)
• A combination between the last lines of one stanza and the first lines of the next stanza

The goal of the problem is to build a model that can predict the author of a group of 4 verses.

Available Files

train.csv

The training dataset, containing the following columns:

• Id – unique identifier for the group of verses
• Versuri – content of 4 verses
• Autor – author of the verses

Example:

test.csv

The testing dataset, which does not contain the Autor column:

• Id – unique identifier
• Versuri – content of 4 verses

Example:

Submission File Format

The submission file must be a CSV with the following columns:

• Id – identifier of the group of verses
• Autor – predicted author

Example:

Notes

• Models can use any natural language processing and machine learning technique.
• Evaluation will be based on prediction accuracy.

Evaluation

Predictions will be compared with the actual labels and accuracy will be calculated:

accuracy = (number_of_correct_predictions / total_number_of_predictions)

The final score is calculated based on the obtained accuracy using the following rules:

• accuracy ≥ 0.9 → 100 points
• accuracy ≤ 0.5 → 0 points
• For intermediate values, proportional scores between 0 and 100 are awarded.