Abstract | ||
---|---|---|
We suggest a new NLG task in the context of the discourse generation pipeline of computational storytelling systems. This task, textual embellishment, is defined by taking a text as input and generating a semantically equivalent output with increased lexical and syntactic complexity. Ideally, this would allow the authors of computational storytellers to implement just lightweight NLG systems and use a domain-independent embellishment module to translate its output into more literary text. We present promising first results on this task using LSTM Encoder-Decoder networks trained on the WikiLarge dataset. Furthermore, we introduce Compiled Computer Tales, a corpus of computationally generated stories, that can be used to test the capabilities of embellishment algorithms. |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/w18-6603 | Natural Language Generation |
Field | DocType | Volume |
Storytelling,Encoder decoder,Computer science,Semantic equivalence,Natural language processing,Artificial intelligence,Syntax | Journal | abs/1810.08076 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Leonid Berov | 1 | 0 | 2.37 |
Kai Standvoss | 2 | 0 | 0.34 |