A Better Variant of Self-Critical Sequence Training
2020-03-22Code Available2· sign in to hype
Ruotian Luo
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ruotianluo/self-critical.pytorchOfficialIn paperpytorch★ 1,006
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| COCO Captions | Transformer_NSC | BLEU-4 | 39.4 | — | Unverified |