Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model.
Chris van der LeeThiago Castro FerreiraChris EmmeryTravis WiltshireEmiel KrahmerPublished in: CoRR (2022)
Keyphrases
- semi supervised learning
- language model
- labeled data
- data sets
- semi supervised
- unlabeled data
- learning models
- training data
- data analysis
- information retrieval
- probabilistic model
- machine learning
- text generation
- data points
- maximum likelihood
- co occurrence
- principal component analysis
- natural language processing
- natural language generation
- label propagation
- pairwise