Data-to-text Generation by Splicing Together Nearest Neighbors
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-right, we learn a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations. Standard techniques for training such a policy require an oracle derivation for each generation, and we prove that finding the shortest such derivation can be reduced to parsing under a particular weighted context-free grammar. We find that policies learned in this way perform on par with strong baselines in terms of automatic and human evaluation, but allow for more interpretable and controllable generation.
Code (1)
Tasks
Conditional Text GenerationData-to-Text GenerationText GenerationSimilar Papers 제목 키워드 기반
CD44 alternative splicing is a sensor of intragenic DNA methylation in tumors
DNA methylation (meDNA) is a suspected modulator of alternative splicing, while splicing in turn is involved in tumour formations nearly as frequently as DNA mutations. Yet, the impact of meDNA on tumorigenesis via its e…
Towards Unconstrained Audio Splicing Detection and Localization with Neural Networks
Freely available and easy-to-use audio editing tools make it straightforward to perform audio splicing. Convincing forgeries can be created by combining various speech samples from the same person. Detection of such spli…
Human DetectionMisinformationGreatSplicing: A Semantically Rich Splicing Dataset
In existing splicing forgery datasets, the insufficient semantic varieties of spliced regions cause a problem that trained detection models overfit semantic features rather than splicing traces. Meanwhile, because of the…
Methods to study splicing from high-throughput RNA Sequencing data
The development of novel high-throughput sequencing (HTS) methods for RNA (RNA-Seq) has provided a very powerful mean to study splicing under multiple conditions at unprecedented depth. However, the complexity of the inf…
Vocal Bursts Intensity PredictionData Augmentation for Transformer-based G2P
The Transformer model has been shown to outperform other neural seq2seq models in several character-level tasks. It is unclear, however, if the Transformer would benefit as much as other seq2seq models from data augmenta…
Data Augmentation