Abstract | ||
---|---|---|
Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model outperforms strong baselines improving the state-of-the-art on the recently released ROTOWIRE dataset. |
Year | Venue | Field |
---|---|---|
2018 | national conference on artificial intelligence | Text generation,Computer science,Neural network architecture,Baseline (configuration management),Artificial intelligence,Artificial neural network,Machine learning,Data records |
DocType | Volume | Citations |
Journal | abs/1809.00582 | 3 |
PageRank | References | Authors |
0.39 | 24 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ratish Puduppully | 1 | 12 | 2.97 |
Li Dong | 2 | 582 | 31.86 |
Mirella Lapata | 3 | 5973 | 369.52 |