Latent Predictor Networks for Code Generation

ACL 2016 Wang LingEdward GrefenstetteKarl Moritz HermannTomáš KočiskýAndrew SeniorFumin WangPhil 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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Code Generation Django lpn (Ling et al., 2016) Accuracy 62.3 # 2
Code Generation Django Phrasal Statistical MT (Ling et al., 2016) Accuracy 31.5 # 3