AGGGEN: Ordering and Aggregating while Generating
arXiv:2106.05580
Abstract
We present AGGGEN (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AGGGEN performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.
arXiv commentCorrect the first citation in the Zero-shot Few-shot scenarios paragraph in Section 7
References in corpus (5)
- Building Natural-Language Generation Systems
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
- Faithful to the Original: Fact Aware Neural Abstractive Summarization
- Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
- Text-to-Text Pre-Training for Data-to-Text Tasks