Code and dataset supporting the paper:
Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White and Rajen Subba. Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue. To appear in Proc. ACL-19.
If you find this code or data useful in your research, please consider citing using the following BibTeX entry:
@InProceedings{Balakrishnan2019constrainednlg,
author = {Anusha Balakrishnan and Jinfeng Rao and Kartikeya Upasani and Michael White and Rajen Subba},
title = {Constrained Decoding for Neural {NLG} from Compositional Representations in Task-Oriented Dialogue},
booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
month = {July},
year = {2019},
note = {To appear}
}
We are currently preparing the dataset and code for release, and plan to add them to this repository as soon as possible. Stay tuned for updates!
Our dataset contains ~34K examples of complex natural language responses in the weather domain. Each response was collected by providing annotators with a user query, a compositional meaning representation (with discourse relations and dialog acts), and a context. All of these are made available in our dataset. See our linked paper for more details.
TreeNLG is released under CC-BY-NC-4.0, see LICENSE for details.