The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models need to share knowledge across languages, which can be achieved through auxiliary tasks for learning a universal representation or cross-lingual mapping. To this end, we propose to exploit both semantic and linguistic features between multiple languages to enhance multilingual translation. On the encoder side, we introduce a disentangling learning task that aligns encoder representations by disentangling semantic and linguistic features, thus facilitating knowledge transfer while preserving complete information. On the decoder side, we leverage a linguistic encoder to integrate low-level linguistic features to assist in the target language generation. Experimental results on multilingual datasets demonstrate significant improvement in zero-shot translation compared to the baseline system, while maintaining performance in supervised translation. Further analysis validates the effectiveness of our method in leveraging both semantic and linguistic features.

Conventional neural machine translation (NMT) models typically use subwords and words as the basic units for model input and comprehension. However, complete words and phrases composed of several tokens are often the fundamental units for expressing semantics, referred to as semantic units. To address this issue, we propose a method Semantic Units for Machine Translation (SU4MT) which models the integral meanings of semantic units within a sentence, and then leverages them to provide a new perspective for understanding the sentence. Specifically, we first propose Word Pair Encoding (WPE), a phrase extraction method to help identify the boundaries of semantic units. Next, we design an Attentive Semantic Fusion (ASF) layer to integrate the semantics of multiple subwords into a single vector: the semantic unit representation. Lastly, the semantic-unit-level sentence representation is concatenated to the token-level one, and they are combined as the input of encoder. Experimental results demonstrate that our method effectively models and leverages semantic-unit-level information and outperforms the strong baselines.

The scaling laws of language models have played a significant role in advancing large language models. In order to promote the development of document translation, we systematically examine the scaling laws in this field. In this paper, we carry out an in-depth analysis of the influence of three factors on translation quality: model scale, data scale, and sequence length. Our findings reveal that increasing sequence length effectively enhances model performance when model size is limited. However, sequence length cannot be infinitely extended; it must be suitably aligned with the model scale and corpus volume. Further research shows that providing adequate context can effectively enhance the translation quality of a document’s initial portion. Nonetheless, exposure bias remains the primary factor hindering further improvement in translation quality for the latter half of the document.

Document-level neural machine translation (DNMT) has shown promising results by incorporating context information through increased maximum lengths of source and target sentences. However, this approach also introduces a length bias problem, whereby DNMT suffers from significant translation quality degradation when decoding sentences that are much shorter or longer than the maximum sentence length during training, i.e., the length bias problem. To prevent the model from neglecting shorter sentences, we sample the training data to ensure a more uniform distribution across different sentence lengths while progressively increasing the maximum sentence length during training. Additionally, we introduce a length-normalized attention mechanism to aid the model in focusing on target information, mitigating the issue of attention divergence when processing longer sentences. Furthermore, during the decoding stage of DNMT, we propose a sliding decoding strategy that limits the length of target sentences to not exceed the maximum length encountered during training. The experimental results indicate that our method can achieve state-of-the-art results on several open datasets, and further analysis shows that our method can significantly alleviate the length bias problem.

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods, which perform multi-objective learning with an auxiliary loss, suffer from the misestimate problem and cannot always achieve a good balance between the previous and new tasks. To solve the problem, we propose a two-stage training method based on the local features of the real loss. We first search low forgetting risk regions, where the model can retain the performance on the previous task as the parameters are updated, to avoid the catastrophic forgetting problem. Then we can continually train the model within this region only with the new training data to fit the new task. Specifically, we propose two methods to search the low forgetting risk regions, which are based on the curvature of loss and the impacts of the parameters on the model output, respectively. We conduct experiments on domain adaptation and more challenging language adaptation tasks, and the experimental results show that our method can achieve significant improvements compared with several strong baselines.

The many-to-many multilingual neural machine translation can translate between language pairs unseen during training, i.e., zero-shot translation. Improving zero-shot translation requires the model to learn universal representations and cross-mapping relationships to transfer the knowledge learned on the supervised directions to the zero-shot directions. In this work, we propose the state mover’s distance based on the optimal theory to model the difference of the representations output by the encoder. Then, we bridge the gap between the semantic-equivalent representations of different languages at the token level by minimizing the proposed distance to learn universal representations. Besides, we propose an agreement-based training scheme, which can help the model make consistent predictions based on the semantic-equivalent sentences to learn universal cross-mapping relationships for all translation directions. The experimental results on diverse multilingual datasets show that our method can improve consistently compared with the baseline system and other contrast methods. The analysis proves that our method can better align the semantic space and improve the prediction consistency.

Although teacher forcing has become the main training paradigm for neural machine translation, it usually makes predictions only conditioned on past information, and hence lacks global planning for the future. To address this problem, we introduce another decoder, called seer decoder, into the encoder-decoder framework during training, which involves future information in target predictions. Meanwhile, we force the conventional decoder to simulate the behaviors of the seer decoder via knowledge distillation. In this way, at test the conventional decoder can perform like the seer decoder without the attendance of it. Experiment results on the Chinese-English, English-German and English-Romanian translation tasks show our method can outperform competitive baselines significantly and achieves greater improvements on the bigger data sets. Besides, the experiments also prove knowledge distillation the best way to transfer knowledge from the seer decoder to the conventional decoder compared to adversarial learning and L2 regularization.

Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages. However, the current multilingual translation paradigm often makes the model tend to preserve the general knowledge, but ignore the language-specific knowledge. Some previous works try to solve this problem by adding various kinds of language-specific modules to the model, but they suffer from the parameter explosion problem and require specialized manual design. To solve these problems, we propose to divide the model neurons into general and language-specific parts based on their importance across languages. The general part is responsible for preserving the general knowledge and participating in the translation of all the languages, while the language-specific part is responsible for preserving the language-specific knowledge and participating in the translation of some specific languages. Experimental results on several language pairs, covering IWSLT and Europarl corpus datasets, demonstrate the effectiveness and universality of the proposed method.

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both general domain and in-domain data. However, the existing methods for domain adaptation usually suffer from catastrophic forgetting, large domain divergence, and model explosion. To address these three problems, we propose a method of “divide and conquer” which is based on the importance of neurons or parameters for the translation model. In this method, we first prune the model and only keep the important neurons or parameters, making them responsible for both general-domain and in-domain translation. Then we further train the pruned model supervised by the original whole model with knowledge distillation. Last we expand the model to the original size and fine-tune the added parameters for the in-domain translation. We conducted experiments on different language pairs and domains and the results show that our method can achieve significant improvements compared with several strong baselines.

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT). The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution. However, low-frequency tokens may carry critical semantic information that will affect the translation quality once they are neglected. In this paper, we explored target token-level adaptive objectives based on token frequencies to assign appropriate weights for each target token during training. We aimed that those meaningful but relatively low-frequency words could be assigned with larger weights in objectives to encourage the model to pay more attention to these tokens. Our method yields consistent improvements in translation quality on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens where we can get 1.68, 1.02, and 0.52 BLEU increases compared with baseline, respectively. Further analyses show that our method can also improve the lexical diversity of translation.

Neural machine translation (NMT) models usually suffer from catastrophic forgetting during continual training where the models tend to gradually forget previously learned knowledge and swing to fit the newly added data which may have a different distribution, e.g. a different domain. Although many methods have been proposed to solve this problem, we cannot get to know what causes this phenomenon yet. Under the background of domain adaptation, we investigate the cause of catastrophic forgetting from the perspectives of modules and parameters (neurons). The investigation on the modules of the NMT model shows that some modules have tight relation with the general-domain knowledge while some other modules are more essential in the domain adaptation. And the investigation on the parameters shows that some parameters are important for both the general-domain and in-domain translation and the great change of them during continual training brings about the performance decline in general-domain. We conducted experiments across different language pairs and domains to ensure the validity and reliability of our findings.

In many practical applications, neural machine translation systems have to deal with the input from automatic speech recognition (ASR) systems which may contain a certain number of errors. This leads to two problems which degrade translation performance. One is the discrepancy between the training and testing data and the other is the translation error caused by the input errors may ruin the whole translation. In this paper, we propose a method to handle the two problems so as to generate robust translation to ASR errors. First, we simulate ASR errors in the training data so that the data distribution in the training and test is consistent. Second, we focus on ASR errors on homophone words and words with similar pronunciation and make use of their pronunciation information to help the translation model to recover from the input errors. Experiments on two Chinese-English data sets show that our method is more robust to input errors and can outperform the strong Transformer baseline significantly.

In domain adaptation for neural machine translation, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitly model the two kinds of information in the encoder-decoder framework so as to exploit out-of-domain data in in-domain training. In our method, we maintain a private encoder and a private decoder for each domain which are used to model domain-specific information. In the meantime, we introduce a common encoder and a common decoder shared by all the domains which can only have domain-independent information flow through. Besides, we add a discriminator to the shared encoder and employ adversarial training for the whole model to reinforce the performance of information separation and machine translation simultaneously. Experiment results show that our method can outperform competitive baselines greatly on multiple data sets.

Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a representation via hierarchical attention networks. However, this method neither considers the relationship between context words nor distinguishes the roles of context words. To address this problem, we propose a query-guided capsule networks to cluster context information into different perspectives from which the target translation may concern. Experiment results show that our method can significantly outperform strong baselines on multiple data sets of different domains.