SOTAVerified

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.

Reproduce

Code

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

DatasetModelMetricClaimedVerifiedStatus
COCO CaptionsTransformer_NSCBLEU-439.4Unverified

Reproductions