Neural Text Generation from Structured Data with Application to the Biography Domain
This work addresses text generation for large-scale, diverse datasets like Wikipedia biographies, though it is incremental as it builds upon existing neural language models.
The paper tackles the problem of generating text from structured data, specifically in the biography domain, by introducing a neural model that mixes a fixed vocabulary with copy actions to handle large vocabularies, achieving a nearly 15 BLEU improvement over a classical baseline.
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.