One important issue that affects the performance of neural machine translation is the scale of available parallel data. For low-resource languages, the amount of parallel data is not sufficient, which results in poor translation quality. In this paper, we propose a diversity data augmentation method that does not use extra monolingual data. We expand the training data by generating diversity pseudo parallel data on the source and target sides. To generate diversity data, the restricted sampling strategy is employed at the decoding steps. Finally, we filter and merge origin data and synthetic parallel corpus to train the final model. In the experiment, the proposed approach achieved 1.96 BLEU points in the IWSLT2014 German–English translation tasks, which was used to simulate a low-resource language. Our approach also consistently and substantially obtained 1.0 to 2.0 BLEU improvement in three other low-resource translation tasks, including English–Turkish, Nepali–English, and Sinhala–English translation tasks.

Benefitting from the rapid development of artificial intelligence (AI) and deep learning, the machine translation task based on neural networks has achieved impressive performance in many high-resource language pairs. However, the neural machine translation (NMT) models still struggle in the translation task on agglutinative languages with complex morphology and limited resources. Inspired by the finding that utilizing the source-side linguistic knowledge can further improve the NMT performance, we propose a multi-source neural model that employs two separate encoders to encode the source word sequence and the linguistic feature sequences. Compared with the standard NMT model, we utilize an additional encoder to incorporate the linguistic features of lemma, part-of-speech (POS) tag, and morphological tag by extending the input embedding layer of the encoder. Moreover, we use a serial combination method to integrate the conditional information from the encoders with the outputs of the decoder, which aims to enhance the neural model to learn a high-quality context representation of the source sentence. Experimental results show that our approach is effective for the agglutinative language translation, which achieves the highest improvements of +2.4 BLEU points on Turkish–English translation task and +0.6 BLEU points on Uyghur–Chinese translation task.

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the teacher model, and in this sense, only strong teacher models are deployed to teach weaker students in practice. However, in low-resource neural machine translation, a stronger teacher model is not available. To counteract this, We therefore propose a novel Teacher-free Knowledge Distillation framework for low-resource neural machine translation, where the model learns from manually designed regularization distribution as a virtual teacher model. The prior distribution of artificial design can not only obtain the similarity information between words, but also provide effective regularity for model training. Experimental results show that the proposed method has improved performance in low-resource language effectively.

Multilingual pre-trained language models (mPLMs) have achieved remarkable performance on zero-shot cross-lingual transfer learning. However, most mPLMs implicitly encourage cross-lingual alignment in pre-training stage, making it hard to capture accurate word alignment across languages. In this paper, we propose Word-align ADapters for Cross-lingual transfer (WAD-X) to explicitly align word representations of mPLMs via language-specific subspace. Taking a mPLM as the backbone model, WAD-X constructs subspace for each source-target language pair via adapters. The adapters use statistical alignment as the prior knowledge to guide word-level aligning in the corresponding bilingual semantic subspace. We evaluate our model across a set of target languages on three zero-shot cross-lingual transfer tasks: part-of-speech tagging (POS), dependency parsing (DP), and sentiment analysis (SA). Experimental results demonstrate that our proposed model improves zero-shot cross-lingual transfer on three benchmarks, with improvements of 2.19, 2.50, and 1.61 points in POS, DP, and SA tasks over strong baselines.

This research was conducted to solve the out-of-vocabulary problem caused by Uyghur spelling errors in Uyghur–Chinese machine translation, so as to improve the quality of Uyghur–Chinese machine translation. This paper assesses three spelling correction methods based on machine translation: 1. Using a Bilingual Evaluation Understudy (BLEU) score; 2. Using a Chinese language model; 3. Using a bilingual language model. The best results were achieved in both the spelling correction task and the machine translation task by using the BLEU score for spelling correction. A maximum F1 score of 0.72 was reached for spelling correction, and the translation result increased the BLEU score by 1.97 points, relative to the baseline system. However, the method of using a BLEU score for spelling correction requires the support of a bilingual parallel corpus, which is a supervised method that can be used in corpus pre-processing. Unsupervised spelling correction can be performed by using either a Chinese language model or a bilingual language model. These two methods can be easily extended to other languages, such as Arabic.

The pre-training fine-tuning mode has been shown to be effective for low resource neural machine translation. In this mode, pre-training models trained on monolingual data are used to initiate translation models to transfer knowledge from monolingual data into translation models. In recent years, pre-training models usually take sentences with randomly masked words as input, and are trained by predicting these masked words based on unmasked words. In this paper, we propose a new pre-training method that still predicts masked words, but randomly replaces some of the unmasked words in the input with their translation words in another language. The translation words are from bilingual data, so that the data for pre-training contains both monolingual data and bilingual data. We conduct experiments on Uyghur-Chinese corpus to evaluate our method. The experimental results show that our method can make the pre-training model have a better generalization ability and help the translation model to achieve better performance. Through a word translation task, we also demonstrate that our method enables the embedding of the translation model to acquire more alignment knowledge.