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

EMNLP 2016  ·  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.

PDF Abstract EMNLP 2016 PDF EMNLP 2016 Abstract

Datasets


Introduced in the Paper:

WikiBio

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Table-to-Text Generation WikiBio Table NLM BLEU 34.70 # 4
ROUGE 25.80 # 3

Methods


No methods listed for this paper. Add relevant methods here