A prominent approach to build datasets for training task-oriented bots is crowd-based paraphrasing. Current approaches, however, assume the crowd would naturally provide diverse paraphrases or focus only on lexical diversity. In this WiP we addressed an overlooked aspect of diversity, introducing an approach for guiding the crowdsourcing process towards paraphrases that are syntactically diverse.
@article{arxiv.2109.09420,
title = {Crowdsourcing Diverse Paraphrases for Training Task-oriented Bots},
author = {Jorge Ramírez and Auday Berro and Marcos Baez and Boualem Benatallah and Fabio Casati},
journal= {arXiv preprint arXiv:2109.09420},
year = {2021}
}