AutoTrain Summarization Predictions for Dutch News

AutoTrain Evaluator contains model predictions for a summarization task on the Dutch version of the CNN/DailyMail dataset. The predictions were generated by the yhavinga/mt5-base-cnn-nl model on the test split. This evaluation snapshot was created by autoevaluate and uploaded on August 2, 2022.

Use Cases

• Benchmarking summarization model performance by comparing predicted summaries against reference texts.
• Analyzing the quality of machine-generated Dutch summaries from the mT5-base-cnn-nl model.
• Studying error patterns in automated text summarization by examining the prediction outputs.

Strengths

• Predictions generated by a specific, named model (yhavinga/mt5-base-cnn-nl) on a defined test split.
• Task and dataset (ml6team/cnn_dailymail_nl) are clearly specified for context.

Limitations

• No column names, sample data, row count, or file size information is available.
• The dataset is a static snapshot from 2022, which may not reflect current model performance.

Provenance

Source

autoevaluate via Hugging Face AutoTrain Evaluator.

Collection Method

Model predictions generated automatically by the AutoTrain platform.

Freshness

Static snapshot from 2022-08-02.