E2E бенчмаркі
material
ID: e2ebenchmark
Related Papers
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
AbstractThe neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and “hallucination”. …...
Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling
AbstractNeural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that …...
Neural Data-to-Text Generation with LM-based Text Augmentation
AbstractFor 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 …...