Learning to Select, Track, and Generate for Data-to-Text
This work addresses content planning and surface realization in data-to-text generation, offering incremental improvements for natural language processing applications.
The authors tackled data-to-text generation by proposing a model with separate tracking and generation modules that simulate human-like writing, and it outperformed existing models across all evaluation metrics, with further improvements from incorporating writer information.
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.