English

Char2char Generation with Reranking for the E2E NLG Challenge

Computation and Language 2018-11-15 v1 Machine Learning

Abstract

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}
}
R2 v1 2026-06-23T05:15:21.994Z