Controlling Neural Language Generation
Large-scale neural language models have made impressive strides in natural language generation. However, typical models operate in a left-to-right, unconstrained fashion with limited control over what is generated. This thesis explores flexible sequence models and weakly supervised methods to perfor...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2022
|
| Online Access: | https://hdl.handle.net/1721.1/144561 https://orcid.org/0000-0001-6101-0163 |