CoCon: A Self-Supervised Approach for Controlled Text Generation
This addresses the need for more precise content control in text generation for applications like creative writing or targeted communication, though it is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of achieving fine-grained control over text generation in pretrained language models, proposing CoCon to incorporate specific content inputs at word- and phrase-level, with results showing it can control attributes like sentiment and topic in a zero-shot manner.
Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LMs is getting attention. While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level. Here, we propose Content-Conditioner (CoCon) to control an LM's output text with a content input, at a fine-grained level. In our self-supervised approach, the CoCon block learns to help the LM complete a partially-observed text sequence by conditioning with content inputs that are withheld from the LM. Through experiments, we show that CoCon can naturally incorporate target content into generated texts and control high-level text attributes in a zero-shot manner.