Operations Guided Neural Networks for High Fidelity Data-To-Text Generation

Abstract

Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.

arXiv commentEMNLP 2018

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• ADADELTA: An Adaptive Learning Rate Method
• Effective Approaches to Attention-based Neural Machine Translation
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Challenges in Data-to-Document Generation
• Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
• Learning to generate one-sentence biographies from Wikidata

Cited by in corpus (2)

• Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation
• Neural Data-to-Text Generation with Dynamic Content Planning