Denoising Auto-encoder Sample Clauses

Denoising Auto-encoder. The auto-encoder is difficult to learn useful knowledge for UNMT without some constraints. Otherwise, it would become a copying task that learned to copy the input words one by one (Xxxxxx et al., 2018a). To alleviate this problem, we utilize the same strategy of denoising auto- encoder (Xxxxxxx et al., 2010), and noise in the form of random token swaps is introduced in this input sentence to improve the model learning ability (Hill et al., 2016; He et al., 2016). The denoising auto-encoder, which encodes a noisy version and reconstructs it with the decoder in the same language, is optimized by minimizing the where PL1→L2 (PL2→L1 ) denotes the translation probability across two languages.