Why is constrained neural language generation particularly challenging?
Abstract: Recent advances in deep neural language models combined with the capacity of large scale datasets have accelerated the development of natural language generation systems that produce fluent and coherent texts (to various degrees of success) in a multitude of tasks and application contexts. However, controlling the output of these models for desired user and task needs is still an open challenge. This is crucial not only to customizing the content and style of the generated language, but also to their safe and reliable deployment in the real world. We present an extensive survey on the emerging topic of constrained neural language generation in which we formally define and categorize the problems of natural language generation by distinguishing between conditions and constraints (the latter being testable conditions on the output text instead of the input), present constrained text generation tasks, and review existing methods and evaluation metrics for constrained text generation. Our aim is to highlight recent progress and trends in this emerging field, informing on the most promising directions and limitations towards advancing the state-of-the-art of constrained neural language generation research.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: We have incorporated the requested changes as detailed by the Action Editor:
- ndnQ's changes
- Provide better contextualization of the future work as requested above
- Fix the references style; citep should be used almost everywhere, so the cites look like (Krause et al., 2020); we have also updated bibliography references to cite published papers instead of ArXiv versions
We highlighted all changes in red as requested for ease of reviewing. Thank you for handling our paper!
Assigned Action Editor: ~Greg_Durrett1
Submission Number: 3303
Loading