Learning from Multiple Sources for Data-to-Text and Text-to-Data

Abstract

Data-to-text (D2T) and text-to-data (T2D) are dual tasks that convert structured data, such as graphs or tables into fluent text, and vice versa. These tasks are usually handled separately and use corpora extracted from a single source. Current systems leverage pre-trained language models fine-tuned on D2T or T2D tasks. This approach has two main limitations: first, a separate system has to be tuned for each task and source; second, learning is limited by the scarcity of available corpora. This paper considers a more general scenario where data are available from multiple heterogeneous sources. Each source, with its specific data format and semantic domain, provides a non-parallel corpus of text and structured data. We introduce a variational auto-encoder model with disentangled style and content variables that allows us to represent the diversity that stems from multiple sources of text and data. Our model is designed to handle the tasks of D2T and T2D jointly. We evaluate our model on several datasets, and show that by learning from multiple sources, our model closes the performance gap with its supervised single-source counterpart and outperforms it in some cases.

arXiv commentAISTATS 2023

References in corpus (15)

• Decoupled Weight Decay Regularization
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Dual Learning for Machine Translation
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
• InfoVAE: Information Maximizing Variational Autoencoders
• Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
• Texygen: A Benchmarking Platform for Text Generation Models
• Semi-Supervised Learning for Neural Machine Translation
• Table-to-text Generation by Structure-aware Seq2seq Learning
• DART: Open-Domain Structured Data Record to Text Generation
• CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
• Variational Template Machine for Data-to-Text Generation
• Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
• On the Latent Holes of VAEs for Text Generation
• Neural data-to-text generation: A comparison between pipeline and end-to-end architectures