A Better Variant of Self-Critical Sequence Training.
2020
In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
37
References
7
Citations
NaN
KQI