Informative Text Generation from Knowledge Triples
This work addresses the limitation of existing KB-to-text models in producing richer, more detailed descriptions, which is important for applications like automated reporting or chatbots, though it is incremental as it builds on standard encoder-decoder architectures.
The paper tackles the problem of generating more informative text from knowledge triples by extending the KB-to-text setting to include additional entity information not in the input, proposing a memory augmented generator that uses a memory network to incorporate learned knowledge during testing, and achieves results with improvements in BLEU scores up to 2.5 points over baselines.
As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data. Among them, KB-to-text aims at converting a set of knowledge triples into human readable sentences. In the original setting, the task assumes that the input triples and the text are exactly aligned in the perspective of the embodied knowledge/information. In this paper, we extend this setting and explore how to facilitate the trained model to generate more informative text, namely, containing more information about the triple entities but not conveyed by the input triples. To solve this problem, we propose a novel memory augmented generator that employs a memory network to memorize the useful knowledge learned during the training and utilizes such information together with the input triples to generate text in the operational or testing phase. We derive a dataset from WebNLG for our new setting and conduct extensive experiments to investigate the effectiveness of our model as well as uncover the intrinsic characteristics of the setting.