Papers › Data-to-Text Generation with Content Selection and Planning
Data-to-Text Generation with Content Selection and Planning
Ratish Puduppully, Li Dong, Mirella Lapata
Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model outperforms strong baselines improving the state-of-the-art on the recently released RotoWire dataset.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Data-to-Text Generation | RotoWire | Neural Content Planning + conditional copy | BLEU | 16.50 | #4 of 6 | Archive leaderboard | report |
| Data-to-Text Generation | RotoWire (Content Ordering) | Neural Content Planning + conditional copy | BLEU | 16.50 | #2 of 5 | Archive leaderboard | report |
| Data-to-Text Generation | RotoWire (Content Ordering) | Neural Content Planning + conditional copy | DLD | 18.58% | #2 of 5 | Archive leaderboard | report |
| Data-to-Text Generation | RotoWire (Relation Generation) | Neural Content Planning + conditional copy | Precision | 87.47% | #5 of 6 | Archive leaderboard | report |
| Data-to-Text Generation | RotoWire (Relation Generation) | Neural Content Planning + conditional copy | count | 34.28 | #5 of 6 | Archive leaderboard | report |
| Data-to-Text Generation | Rotowire (Content Selection) | Neural Content Planning + conditional copy | Precision | 34.18% | #3 of 5 | Archive leaderboard | report |
| Data-to-Text Generation | Rotowire (Content Selection) | Neural Content Planning + conditional copy | Recall | 51.22% | #3 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections