Performance Comparison of Statistical vs. Neural-Based Translation System on Low-Resource Languages

Figure 1:

Figure 2:

Figure 3:

Figure 4:

Figure 5:

Figure 6:

Figure 7:

Figure 8:

Figure 9:

Figure 10:

Attention-based NMT outperforms SMT for the Bengali–Hindi language pair (Das et al. [32])

NMT outperformed SMT with transfer learning, ensemble, and further processing of data (Zopth et al.)

NMT system with transformer model and BPE outperformed phrase-based SMT for English–Hindi and Hindi–English language pairs (Haque et al. [33])

English–Hindi translation using different optimizers

English–Bengali translation BLEU scores using different optimizers

BLEU-1, 2, and 3 scores are summarized for Eng.–Beng. and Eng.–Hindi language pairs using Adam- and SGD-Optimizers

For various low-resource corpus SMT outperformed NMT (Ahmadnia et al. [17])