This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing delexicalization (relexicalization) steps at the word-level to handle rare words. By contrast, we train a simple character level seq2seq model, which requires no pre/post-processing (delexicalization, tokenization or even lowercasing), with surprisingly good results. For further improvement, we explore two re-ranking approaches for scoring candidates. We also introduce a synthetic dataset creation procedure, which opens up a new way of creating artificial datasets for Natural Language Generation.
Cite
@article{arxiv.1811.05826,
title = {Char2char Generation with Reranking for the E2E NLG Challenge},
author = {Shubham Agarwal and Marc Dymetman and Eric Gaussier},
journal= {arXiv preprint arXiv:1811.05826},
year = {2018}
}