Directly training a document-to-document (Doc2Doc) neural machine translation (NMT) via Transformer from scratch, especially on small datasets, usually fails to converge. Our dedicated probing tasks show that 1) both the absolute position and relative position information gets gradually weakened or even vanished once it reaches the upper encoder layers, and 2) the vanishing of absolute position information in encoder output causes the training failure of Doc2Doc NMT. To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention. Specifically, we integrate absolute positional information, i.e., position embeddings, into the query-key pairs both in self-attention and cross-attention through a simple yet effective addition operation. Moreover, we also integrate relative position encoding in self-attention. The proposed P-Transformer utilizes sinusoidal position encoding and does not require any task-specified position embedding, segment embedding, or attention mechanism. Through the above methods, we build a Doc2Doc NMT model with P-Transformer, which ingests the source document and completely generates the target document in a sequence-to-sequence (seq2seq) way. In addition, P-Transformer can be applied to seq2seq-based document-to-sentence (Doc2Sent) and sentence-to-sentence (Sent2Sent) translations. Extensive experimental results of Doc2Doc NMT show that P-Transformer significantly outperforms strong baselines on the widely-used 9 document-level datasets in 7 language pairs, covering small-, middle-, and large-scales, and achieves a new state-of-the-art. Experimentation on discourse phenomena shows that our Doc2Doc NMT models improve the translation quality in both BLEU and discourse coherence. We make our code available on Github.

Subword segmentation plays an important role in Tibetan neural machine translation (NMT). The structure of Tibetan words consists of two levels. First, words consist of a sequence of syllables, and then a syllable consists of a sequence of characters. According to this special word structure, we propose two methods for Tibetan subword segmentation, namely syllable-based and character-based methods. The former generates subwords based on the Tibetan syllables, and the latter is based on Tibetan characters. In addition, we carry out experiments with these two subword segmentation methods on low-resource Tibetan-to-Chinese NMT, respectively. The experimental results show that both of them can improve translation performance, in which the subword segmentation based on character sequences can achieve better results. Overall, our proposed character-based subword segmentation is more simple and effective. Moreover, it can achieve better experimental results without paying much attention to the linguistic features of Tibetan.

In this article, we show that word translations can be explicitly incorporated into NMT effectively to avoid wrong translations. Specifically, we propose three cross-lingual encoders to explicitly incorporate word translations into NMT: (1) Factored encoder, which encodes a word and its translation in a vertical way; (2) Gated encoder, which uses a gated mechanism to selectively control the amount of word translations moving forward; and (3) Mixed encoder, which stitchingly learns a word and its translation annotations over sequences where words and their translations are alternatively mixed. Besides, we first use a simple word dictionary approach and then a word sense disambiguation (WSD) approach to effectively model the word context for better word translation. Experimentation on Chinese-to-English translation demonstrates that all proposed encoders are able to improve the translation accuracy for both traditional RNN-based NMT and recent self-attention-based NMT (hereafter referred to as Transformer ). Specifically, Mixed encoder yields the most significant improvement of 2.0 in BLEU on the RNN-based NMT, while Gated encoder improves 1.2 in BLEU on Transformer . This indicates the usefulness of an WSD approach in modeling word context for better word translation. This also indicates the effectiveness of our proposed cross-lingual encoders in explicitly modeling word translations to avoid wrong translations in NMT. Finally, we discuss in depth how word translations benefit different NMT frameworks from several perspectives.

In neural machine translation (NMT), the source and target words are at the two ends of a large deep neural network, normally mediated by a series of non-linear activations. The problem with such consequent non-linear activations is that they significantly decrease the magnitude of the gradient in a deep neural network, and thus gradually loosen the interaction between source words and their translations. As a result, a source word may be incorrectly translated into a target word out of its translational equivalents. In this article, we propose short-path units (SPUs) to strengthen the association of source and target words by allowing information flow over adjacent layers effectively via linear interpolation. In particular, we enrich three critical NMT components with SPUs: (1) an enriched encoding model with SPU, which interpolates source word embeddings linearly into source annotations; (2) an enriched decoding model with SPU, which enables the source context linearly flow to target-side hidden states; and (3) an enriched output model with SPU, which further allows linear interpolation of target-side hidden states into output states. Experimentation on Chinese-to-English, English-to-German, and low-resource Tibetan-to-Chinese translation tasks demonstrates that the linear interpolation of SPUs significantly improves the overall translation quality by 1.88, 1.43, and 3.75 BLEU, respectively. Moreover, detailed analysis shows that our approaches much strengthen the association of source and target words. From the preceding, we can see that our proposed model is effective both in rich- and low-resource scenarios.

In the popular sequence to sequence (seq2seq) neural machine translation (NMT), there exist many weighted sum models (WSMs), each of which takes a set of input and generates one output. However, the weights in a WSM are independent of each other and fixed for all inputs, suggesting that by ignoring different needs of inputs, the WSM lacks effective control on the influence of each input. In this paper, we propose adaptive weighting for WSMs to control the contribution of each input. Specifically, we apply adaptive weighting for both GRU and the output state in NMT. Experimentation on Chinese-to-English translation and English-to-German translation demonstrates that the proposed adaptive weighting is able to much improve translation accuracy by achieving significant improvement of 1.49 and 0.92 BLEU points for the two translation tasks. Moreover, we discuss in-depth on what type of information is encoded in the encoder and how information influences the generation of target words in the decoder.