SeqPlan SportSett Text Benchmark Dataset

Presenting a submission to the GEM benchmark for text modality tasks. It contains text data from the SeqPlan-SportSett project, with a size category of 1K rows. The dataset was last updated in April 2022.

Use Cases

• Evaluate text generation models on the SeqPlan-SportSett task as part of the GEM benchmark.
• Analyze text data for the 'text' modality specified in the dataset tags.
• Benchmark natural language processing systems using the provided JSON format data.

Strengths

• Dataset is part of the GEM benchmark, a standard for evaluation.
• Tagged with a specific size category of 1K rows.
• Includes tags specifying the 'text' modality and 'JSON' format.

Limitations

• The exact number of rows, columns, and sample data are unknown.
• Dataset description and specific features are minimal, providing little context.
• Last updated in 2022, which may limit relevance for current model evaluation.

Provenance

Source

GEM-submissions

Collection Method

GEM Submission named SeqPlan-SportSett.

Freshness

Last updated on 2022-04-21.

Geography

Region tag indicates 'us'.