Learning to Diversify Neural Text Generation via Degenerative Model
This addresses the issue of low diversity in text generation for applications like dialogue systems, though it is incremental as it builds on existing methods for penalizing degeneration.
The paper tackles the problem of neural language models generating repetitive and uninformative text by proposing a method that trains two models: one to amplify undesirable patterns and another to focus on patterns the first fails to learn, resulting in improved diversity in language modeling and dialogue generation tasks.
Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable behaviors (e.g., repetition, overuse of frequent words) from language models, we propose an alternative approach based on an observation: models primarily learn attributes within examples that are likely to cause degeneration problems. Based on this observation, we propose a new approach to prevent degeneration problems by training two models. Specifically, we first train a model that is designed to amplify undesirable patterns. We then enhance the diversity of the second model by focusing on patterns that the first model fails to learn. Extensive experiments on two tasks, namely language modeling and dialogue generation, demonstrate the effectiveness of our approach.