Improving Sign Language Translation with Monolingual Data by Sign Back-Translation

Despite existing pioneering works on sign language translation (SLT), there is a non-trivial obstacle, i.e., the limited quantity of parallel sign-text data. To tackle this parallel data bottleneck, we propose a sign back-translation (SignBT) approach, which incorporates massive spoken language texts into SLT training. With a text-to-gloss translation model, we first back-translate the monolingual text to its gloss sequence. Then, the paired sign sequence is generated by splicing pieces from an estimated gloss-to-sign bank at the feature level. Finally, the synthetic parallel data serves as a strong supplement for the end-to-end training of the encoder-decoder SLT framework. To promote the SLT research, we further contribute CSL-Daily, a large-scale continuous SLT dataset. It provides both spoken language translations and gloss-level annotations. The topic revolves around people's daily lives (e.g., travel, shopping, medical care), the most likely SLT application scenario. Extensive experimental results and analysis of SLT methods are reported on CSL-Daily. With the proposed sign back-translation method, we obtain a substantial improvement over previous state-of-the-art SLT methods.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract


Introduced in the Paper:


Used in the Paper:

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sign Language Recognition CSL-Daily BN-TIN+Transf. Word Error Rate (WER) 33.1 # 8
Sign Language Translation CSL-Daily BN-TIN-Transf. BLEU-4 13.19 # 7
Sign Language Translation CSL-Daily BN-TIN-Transf.+SignBT BLEU-4 21.34 # 4
Sign Language Recognition RWTH-PHOENIX-Weather 2014 T SignBT Word Error Rate (WER) 23.9 # 7
Sign Language Translation RWTH-PHOENIX-Weather 2014 T BN-TIN-Transf.+SignBT BLEU-4 24.32 # 5
Sign Language Translation RWTH-PHOENIX-Weather 2014 T BN-TIN-Transf. BLEU-4 21.68 # 7


No methods listed for this paper. Add relevant methods here