This dataset consists of (human-written) NBA basketball game summaries aligned with their corresponding box- and line-scores. Summaries taken from rotowire.com are referred to as the "rotowire" data. There are 4853 distinct rotowire summaries, covering NBA games played between 1/1/2014 and 3/29/2017; some games have multiple summaries. The summaries have been randomly split into training, validation, and test sets consisting of 3398, 727, and 728 summaries, respectively.
Source: Challenges in Data-to-Document Generation
Image Source: https://arxiv.org/pdf/1707.08052v1.pdf
Variants: RotoWire (Relation Generation), Rotowire (Content Selection), RotoWire (Content Ordering), RotoWire
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Data-to-Text Generation | Force-Copy | May the Force Be with … | 2021-12-20 |
| Data-to-Text Generation | Macro | Data-to-text Generation with Macro Planning | 2021-02-04 |
| Data-to-Text Generation | Hierarchical transformer encoder + conditional copy | A Hierarchical Model for Data-to-Text … | 2019-12-20 |
| Data-to-Text Generation | Neural Content Planning + conditional copy | Data-to-Text Generation with Content Selection … | 2018-09-03 |
| Data-to-Text Generation | Encoder-decoder + conditional copy | Challenges in Data-to-Document Generation | 2017-07-25 |
Recent papers with results on this dataset: