Papers › Latent Predictor Networks for Code Generation

Latent Predictor Networks for Code Generation

22 Mar 2016ACL 2016 8arXiv:1603.06744archive 2025-07-28

Wang Ling, Edward Grefenstette, Karl Moritz Hermann, Tomáš Kočiský, Andrew Senior, Fumin Wang, Phil Blunsom

Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of input functions. Crucially, our approach allows both the choice of conditioning context and the granularity of generation, for example characters or tokens, to be marginalised, thus permitting scalable and effective training. Using this framework, we address the problem of generating programming code from a mixed natural language and structured specification. We create two new data sets for this paradigm derived from the collectible trading card games Magic the Gathering and Hearthstone. On these, and a third preexisting corpus, we demonstrate that marginalising multiple predictors allows our model to outperform strong benchmarks.

PaperPDFConference PDFCode

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

Code

deepmind/card2code officialmentioned on GitHubNOASSERTION report
davidgolub/QuestionGeneration mentioned on GitHubpytorchNOASSERTION 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

Card GamesCode GenerationText Generation

Datasets

Introduced by this paper, per the archive.

Hearthstone

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation Django lpn (Ling et al., 2016) Accuracy 62.3 #10 of 11 Archive leaderboard report
Code Generation Django lpn (Ling et al., 2016) BLEU Score 77.6 #10 of 11 Archive leaderboard report
Code Generation Django Phrasal Statistical MT (Ling et al., 2016) Accuracy 31.5 #11 of 11 Archive leaderboard report
Code Generation Django Phrasal Statistical MT (Ling et al., 2016) BLEU Score 47.6 #11 of 11 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