Search and Learning for Unsupervised Text Generation
This approach is significant for industry applications in building minimal viable products and for social impacts by reducing annotation labor and aiding low-resource languages, though it is incremental as it builds on existing search and learning techniques.
The paper tackles the problem of unsupervised text generation by proposing a method that uses heuristic objective functions and discrete search algorithms to generate sentences, followed by a machine learning model to refine the results, achieving efficiency improvements without requiring labeled data.
With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional text generation systems are trained in a supervised way, requiring massive labeled parallel corpora. In this paper, I will introduce our recent work on search and learning approaches to unsupervised text generation, where a heuristic objective function estimates the quality of a candidate sentence, and discrete search algorithms generate a sentence by maximizing the search objective. A machine learning model further learns from the search results to smooth out noise and improve efficiency. Our approach is important to the industry for building minimal viable products for a new task; it also has high social impacts for saving human annotation labor and for processing low-resource languages.