82 citations · 266 across the 17 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CL2021
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation
Mingkai Deng, Bowen Tan, Zhengzhong Liu +2
Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity make…
cs.CL2021★ 14 cited
Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
Han Guo, Bowen Tan, Zhengzhong Liu +2
Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable t…