Learning to Select, Track, and Generate for Data-to-Text

Abstract

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generation. Experimental results show that our model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.

ACL 2019

References in corpus (5)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• On the Convergence of Adam and Beyond
• DyNet: The Dynamic Neural Network Toolkit

Cited by in corpus (7)

• Revisiting Challenges in Data-to-Text Generation with Fact Grounding
• ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
• Fact-based Text Editing
• Data-to-Text Generation with Style Imitation
• Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation
• AutoChart: A Dataset for Chart-to-Text Generation Task
• Shared Task on Evaluating Accuracy in Natural Language Generation