Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation

Shuming Ma, Pengcheng Yang, Tianyu Liu, Peng Li, Jie Zhou, Xu Sun


Abstract
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 score.
Anthology ID:
P19-1197
Original:
P19-1197v1
Version 2:
P19-1197v2
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2047–2057
Language:
URL:
https://aclanthology.org/P19-1197
DOI:
10.18653/v1/P19-1197
Bibkey:
Cite (ACL):
Shuming Ma, Pengcheng Yang, Tianyu Liu, Peng Li, Jie Zhou, and Xu Sun. 2019. Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2047–2057, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation (Ma et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1197.pdf
Code
 lancopku/Pivot
Data
WikiBio