Text Generation with Exemplar-based Adaptive Decoding
This addresses text generation for NLP applications, but it is incremental as it builds on the encoder-decoder paradigm with a novel adaptation.
The paper tackles text generation by using retrieved exemplars as soft templates to guide decoding, achieving strong performance and outperforming baselines in abstractive summarization and data-to-text tasks.
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.