Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack of large parallel data is a major practical problem for many domains. In this work, we consider the scenario of low resource table-to-text generation, where only limited parallel data is available. We propose a novel model to separate the generation into two stages: key fact prediction and surface realization. It first predicts the key facts from the tables, and then generates the text with the key facts. The training of key fact prediction needs much fewer annotated data, while surface realization can be trained with pseudo parallel corpus. We evaluate our model on a biography generation dataset. Our model can achieve 27.34 BLEU score with only 1, 000 parallel data, while the baseline model only obtain the performance of 9.71 BLEU score1.
CITATION STYLE
Ma, S., Yang, P., Liu, T., Li, P., Zhou, J., & Sun, X. (2020). Key fact as pivot: A two-stage model for low resource table-to-text generation. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 2047–2057). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p19-1197
Mendeley helps you to discover research relevant for your work.