Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network. The capacity of the memory network that detecting the most relevant part of the current sentence from memory renders a natural solution to model the rich document-level context. In this work, the proposed document-aware memory network is implemented to enhance the Transformer NMT baseline. Experiments on several tasks show that the proposed method significantly improves the NMT performance over strong Transformer baselines and other related studies.

Non-autoregressive generation has attracted more and more attention due to its fast decoding speed. Latent alignment objectives, such as CTC, are designed to capture the monotonic alignments between the predicted and output tokens, which have been used for machine translation and sentence summarization. However, our preliminary experiments revealed that CTC performs poorly on document abstractive summarization, where a high compression ratio between the input and output is involved. To address this issue, we conduct a theoretical analysis and propose Hierarchical Latent Alignment (HLA). The basic idea is a two-step alignment process: we first align the sentences in the input and output, and subsequently derive token-level alignment using CTC based on aligned sentences. We evaluate the effectiveness of our proposed approach on two widely used datasets XSUM and CNNDM. The results indicate that our proposed method exhibits remarkable scalability even when dealing with high compression ratios.

Learning semantic representation for translation context is beneficial to statistical machine translation (SMT). Previous efforts have focused on implicitly encoding syntactic and semantic knowledge in translation context by neural networks, which are weak in capturing explicit structural syntax information. In this paper, we propose a new neural network with a tree-based convolutional architecture to explicitly learn structural syntax information in translation context, thus improving translation prediction. Specifically, we first convert parallel sentences with source parse trees into syntax-based linear sequences based on a minimum syntax subtree algorithm, and then define a tree-based convolutional network over the linear sequences to learn syntax-based context representation and translation prediction jointly. To verify the effectiveness, the proposed model is integrated into phrase-based SMT. Experiments on large-scale Chinese-to-English and German-to-English translation tasks show that the proposed approach can achieve a substantial and significant improvement over several baseline systems.

Attention mechanism, which selectively focuses on source-side information to learn a context vector for generating target words, has been shown to be an effective method for neural machine translation (NMT). In fact, generating target words depends on not only the source-side information but also the target-side information. Although the vanilla NMT can acquire target-side information implicitly by recurrent neural networks (RNN), RNN cannot adequately capture the global relationship between target-side words. To solve this problem, this paper proposes a novel target-attention approach to capture this information, thus enhancing target word predictions in NMT. Specifically, we propose three variants of target-attention model to directly obtain the global relationship among target words: 1) a forward target-attention model that uses a target attention mechanism to incorporate previous historical target words into the prediction of the current target word; 2) a reverse target-attention model that adopts a reverse RNN model to obtain the entire reverse target words information, and then to combine with source context information to generate target sequence; 3) a bidirectional target-attention model that combines the forward target-attention model and reverse target-attention model together, which can make full use of target words to further improve the performance of NMT. Our methods can be integrated into both RNN based NMT and self-attention based NMT, and help NMT get global target-side information to improve translation performance. Experiments on the NIST Chinese-to-English and the WMT English-to-German translation tasks show that the proposed models achieve significant improvements over state-of-the-art baselines.