Papers › Neural Text Generation from Structured Data with Application to the Biography Domain

Neural Text Generation from Structured Data with Application to the Biography Domain

24 Mar 2016EMNLP 2016 11arXiv:1603.07771archive 2025-07-28

Remi Lebret, David Grangier, Michael Auli

This paper introduces a neural model for concept-to-text generation that scales to large, rich domains. We experiment with a new dataset of biographies from Wikipedia that is an order of magnitude larger than existing resources with over 700k samples. The dataset is also vastly more diverse with a 400k vocabulary, compared to a few hundred words for Weathergov or Robocup. Our model builds upon recent work on conditional neural language model for text generation. To deal with the large vocabulary, we extend these models to mix a fixed vocabulary with copy actions that transfer sample-specific words from the input database to the generated output sentence. Our neural model significantly out-performs a classical Kneser-Ney language model adapted to this task by nearly 15 BLEU.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

nathanlesage/so-classifier mentioned on GitHubpytorch report
parajain/data-to-text mentioned on GitHub report

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

Concept-To-Text GenerationLanguage ModelingLanguage ModellingSentenceTable-to-Text GenerationText Generation

Datasets

Introduced by this paper, per the archive.

WikiBio

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Table-to-Text Generation WikiBio Table NLM BLEU 34.70 #4 of 4 Archive leaderboard report
Table-to-Text Generation WikiBio Table NLM ROUGE 25.80 #4 of 4 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