Pragmatically Informative Text Generation
This work addresses the issue of generating more informative text for natural language processing tasks, though it is incremental as it builds on existing systems.
The paper tackled the problem of improving informativeness in conditional text generation by applying computational pragmatics techniques, resulting in enhanced performance for abstractive summarization and generation from structured meaning representations.
We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game between speakers and listeners, in which a speaker should generate output text that a listener can use to correctly identify the original input that the text describes. While such approaches are widely used in cognitive science and grounded language learning, they have received less attention for more standard language generation tasks. We consider two pragmatic modeling methods for text generation: one where pragmatics is imposed by information preservation, and another where pragmatics is imposed by explicit modeling of distractors. We find that these methods improve the performance of strong existing systems for abstractive summarization and generation from structured meaning representations.