Natural Language Generation through Character-based RNNs with Finite-state Prior Knowledge

Raghav Goyal, Marc Dymetman, Eric Gaussier


Abstract
Recently Wen et al. (2015) have proposed a Recurrent Neural Network (RNN) approach to the generation of utterances from dialog acts, and shown that although their model requires less effort to develop than a rule-based system, it is able to improve certain aspects of the utterances, in particular their naturalness. However their system employs generation at the word-level, which requires one to pre-process the data by substituting named entities with placeholders. This pre-processing prevents the model from handling some contextual effects and from managing multiple occurrences of the same attribute. Our approach uses a character-level model, which unlike the word-level model makes it possible to learn to “copy” information from the dialog act to the target without having to pre-process the input. In order to avoid generating non-words and inventing information not present in the input, we propose a method for incorporating prior knowledge into the RNN in the form of a weighted finite-state automaton over character sequences. Automatic and human evaluations show improved performance over baselines on several evaluation criteria.
Anthology ID:
C16-1103
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
1083–1092
URL:
https://www.aclweb.org/anthology/C16-1103
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/C16-1103.pdf