We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as "soft templates," which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text generation. Empirical results show that this model achieves strong performance and outperforms comparable baselines.
@article{arxiv.1904.04428,
title = {Text Generation with Exemplar-based Adaptive Decoding},
author = {Hao Peng and Ankur P. Parikh and Manaal Faruqui and Bhuwan Dhingra and Dipanjan Das},
journal= {arXiv preprint arXiv:1904.04428},
year = {2019}
}