ﻻ يوجد ملخص باللغة العربية
Recent advancements in data-to-text generation largely take on the form of neural end-to-end systems. Efforts have been dedicated to improving text generation systems by changing the order of training samples in a process known as curriculum learning. Past research on sequence-to-sequence learning showed that curriculum learning helps to improve both the performance and convergence speed. In this work, we delve into the same idea surrounding the training samples consisting of structured data and text pairs, where at each update, the curriculum framework selects training samples based on the models competence. Specifically, we experiment with various difficulty metrics and put forward a soft edit distance metric for ranking training samples. Our benchmarks show faster convergence speed where training time is reduced by 38.7% and performance is boosted by 4.84 BLEU.
For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text samples a
We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage. We suggest four extensions to tha
We propose a shared task on training instance selection for few-shot neural text generation. Large-scale pretrained language models have led to dramatic improvements in few-shot text generation. Nonetheless, almost all previous work simply applies ra
Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of natural langu
Neural data-to-text generation models have achieved significant advancement in recent years. However, these models have two shortcomings: the generated texts tend to miss some vital information, and they often generate descriptions that are not consi