تقرير
Faster Transformer Decoding: N-gram Masked Self-Attention
العنوان: | Faster Transformer Decoding: N-gram Masked Self-Attention |
---|---|
المؤلفون: | Chelba, Ciprian, Chen, Mia, Bapna, Ankur, Shazeer, Noam |
سنة النشر: | 2020 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Computation and Language, Statistics - Machine Learning |
الوصف: | Motivated by the fact that most of the information relevant to the prediction of target tokens is drawn from the source sentence $S=s_1, \ldots, s_S$, we propose truncating the target-side window used for computing self-attention by making an $N$-gram assumption. Experiments on WMT EnDe and EnFr data sets show that the $N$-gram masked self-attention model loses very little in BLEU score for $N$ values in the range $4, \ldots, 8$, depending on the task. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2001.04589 |
رقم الأكسشن: | edsarx.2001.04589 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |