In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for the improvement of about +1 BLEU across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.
Low-resource African languages have not fully benefited from the progress in neural machine translation because of a lack of data. Motivated by this challenge we compare zero-shot learning, transfer learning and multilingual learning on three Bantu languages (Shona, isiXhosa and isiZulu) and English. Our main target is English-to-isiZulu translation for which we have just 30,000 sentence pairs, 28% of the average size of our other corpora. We show the importance of language similarity on the performance of English-to-isiZulu transfer learning based on English-to-isiXhosa and English-to-Shona parent models whose BLEU scores differ by 5.2. We then demonstrate that multilingual learning surpasses both transfer learning and zero-shot learning on our dataset, with BLEU score improvements relative to the baseline English-to-isiZulu model of 9.9, 6.1 and 2.0 respectively. Our best model also improves the previous SOTA BLEU score by more than 10.
This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations from LMVR and MORSEL. We evaluate translation tasks between English and each of Nepali, Sinhala, and Kazakh, and predict that using morphologically-based segmentation methods would lead to better performance in this setting. However, comparing to BPE, we find that no consistent and reliable differences emerge between the segmentation methods. While morphologically-based methods outperform BPE in a few cases, what performs best tends to vary across tasks, and the performance of segmentation methods is often statistically indistinguishable.
Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen at the meta-training stage. In this paper, we aim to alleviate this issue by proposing a novel meta-curriculum learning for domain adaptation in NMT. During meta-training, the NMT first learns the similar curricula from each domain to avoid falling into a bad local optimum early, and finally learns the curricula of individualities to improve the model robustness for learning domain-specific knowledge. Experimental results on 10 different low-resource domains show that meta-curriculum learning can improve the translation performance of both familiar and unfamiliar domains. All the codes and data are freely available at https://github.com/NLP2CT/Meta-Curriculum.
Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important. Here, we investigate the effective use of training data for low-resource NMT. In particular, we propose a dynamic curriculum learning (DCL) method to reorder training samples in training. Unlike previous work, we do not use a static scoring function for reordering. Instead, the order of training samples is dynamically determined in two ways - loss decline and model competence. This eases training by highlighting easy samples that the current model has enough competence to learn. We test our DCL method in a Transformer-based system. Experimental results show that DCL outperforms several strong baselines on three low-resource machine translation benchmarks and different sized data of WMT' 16 En-De.
Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have explored using the readily available monolingual data in either or both of the languages to improve the standard of translation models in low, and even high, resource languages. One of the most successful of such works is the back-translation that utilizes the translations of the target language monolingual data to increase the amount of the training data. The quality of the backward model which is trained on the available parallel data has been shown to determine the performance of the back-translation approach. Despite this, only the forward model is improved on the monolingual target data in standard back-translation. A previous study proposed an iterative back-translation approach for improving both models over several iterations. But unlike in the traditional back-translation, it relied on both the target and source monolingual data. This work, therefore, proposes a novel approach that enables both the backward and forward models to benefit from the monolingual target data through a hybrid of self-learning and back-translation respectively. Experimental results have shown the superiority of the proposed approach over the traditional back-translation method on English-German low resource neural machine translation. We also proposed an iterative self-learning approach that outperforms the iterative back-translation while also relying only on the monolingual target data and require the training of less models.
Language pairs with limited amounts of parallel data, also known as low-resource languages, remain a challenge for neural machine translation. While the Transformer model has achieved significant improvements for many language pairs and has become the de facto mainstream architecture, its capability under low-resource conditions has not been fully investigated yet. Our experiments on different subsets of the IWSLT14 training data show that the effectiveness of Transformer under low-resource conditions is highly dependent on the hyper-parameter settings. Our experiments show that using an optimized Transformer for low-resource conditions improves the translation quality up to 7.3 BLEU points compared to using the Transformer default settings.
Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model trained on a high-resource language-pair and fine-tuning it on the data of the low-resource MT condition of interest. However, it is not clear generally which high-resource language-pair offers the best transfer learning for the target MT setting. Furthermore, different transferred models may have complementary semantic and/or syntactic strengths, hence using only one model may be sub-optimal. In this paper, we tackle this problem using knowledge distillation, where we propose to distill the knowledge of ensemble of teacher models to a single student model. As the quality of these teacher models varies, we propose an effective adaptive knowledge distillation approach to dynamically adjust the contribution of the teacher models during the distillation process. Experiments on transferring from a collection of six language pairs from IWSLT to five low-resource language-pairs from TED Talks demonstrate the effectiveness of our approach, achieving up to +0.9 BLEU score improvement compared to strong baselines.
Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as character-level translation, which further simplified model designing, but there is a performance gap between the translation-based approach and other methods. This motivates our work, in which we apply the best practices from low-resource neural machine translation to supervised Chinese segmentation. We examine a series of techniques including regularization, data augmentation, objective weighting, transfer learning, and ensembling. Compared to previous works, our low-resource translation-based method maintains the effortless model design, yet achieves the same result as state of the art in the constrained evaluation without using additional data.
Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the backward system - which is trained on the available parallel data and used for the back-translation - has been shown in many studies to affect the performance of the final NMT model. In low resource conditions, the available parallel data is usually not enough to train a backward model that can produce the qualitative synthetic data needed to train a standard translation model. This work proposes a self-training strategy where the output of the backward model is used to improve the model itself through the forward translation technique. The technique was shown to improve baseline low resource IWSLT'14 English-German and IWSLT'15 English-Vietnamese backward translation models by 11.06 and 1.5 BLEUs respectively. The synthetic data generated by the improved English-German backward model was used to train a forward model which out-performed another forward model trained using standard back-translation by 2.7 BLEU.
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via multilingual NMT. The second direction employs monolingual data with self-supervision to pre-train translation models, followed by fine-tuning on small amounts of supervised data. In this work, we join these two lines of research and demonstrate the efficacy of monolingual data with self-supervision in multilingual NMT. We offer three major results: (i) Using monolingual data significantly boosts the translation quality of low-resource languages in multilingual models. (ii) Self-supervision improves zero-shot translation quality in multilingual models. (iii) Leveraging monolingual data with self-supervision provides a viable path towards adding new languages to multilingual models, getting up to 33 BLEU on ro-en translation without any parallel data or back-translation.
The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel approach to incorporate a LM as prior in a neural translation model (TM). Specifically, we add a regularization term, which pushes the output distributions of the TM to be probable under the LM prior, while avoiding wrong predictions when the TM "disagrees" with the LM. This objective relates to knowledge distillation, where the LM can be viewed as teaching the TM about the target language. The proposed approach does not compromise decoding speed, because the LM is used only at training time, unlike previous work that requires it during inference. We present an analysis of the effects that different methods have on the distributions of the TM. Results on two low-resource machine translation datasets show clear improvements even with limited monolingual data.
Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo, Somali [SATOS]). We collected the available resources on the SATOS languages to evaluate the current state of NMT for LRLs. Our evaluation, comparing a baseline single language pair NMT model against semi-supervised learning, transfer learning, and multilingual modeling, shows significant performance improvements both in the En-LRL and LRL-En directions. In terms of averaged BLEU score, the multilingual approach shows the largest gains, up to +5 points, in six out of ten translation directions. To demonstrate the generalization capability of each model, we also report results on multi-domain test sets. We release the standardized experimental data and the test sets for future works addressing the challenges of NMT in under-resourced settings, in particular for the SATOS languages.
Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to mitigate this problem, such as transfer learning, semi-supervised and unsupervised learning techniques. In this paper, we review the existing methods, where the main idea is to exploit the power of monolingual data, which, compared to parallel, is usually easier to obtain and significantly greater in amount.
Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom parent model or at least update an existing parent model's vocabulary for each child language pair they wish to train, in an effort to align parent and child vocabularies. This is not a practical solution. It is wasteful to devote the majority of training time for new language pairs to optimizing parameters on an unrelated data set. Further, this overhead reduces the utility of neural machine translation for deployment in humanitarian assistance scenarios, where extra time to deploy a new language pair can mean the difference between life and death. In this work, we present a `universal' pre-trained neural parent model with constant vocabulary that can be used as a starting point for training practically any new low-resource language to a fixed target language. We demonstrate that our approach, which leverages orthography unification and a broad-coverage approach to subword identification, generalizes well to several languages from a variety of families, and that translation systems built with our approach can be built more quickly than competing methods and with better quality as well.
While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translation tasks show that uncertainty-based confidence estimation significantly improves the performance of back-translation.
This paper proposes a novel multilingual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese--Russian pair for benchmarking. Although there are many solutions for low-resource scenarios, such as multilingual NMT and back-translation, we have empirically confirmed their limited success when restricted to in-domain data. We therefore propose to exploit out-of-domain data through transfer learning, by using it to first train a multilingual NMT model followed by multistage fine-tuning on in-domain parallel and back-translated pseudo-parallel data. Our approach, which combines domain adaptation, multilingualism, and back-translation, helps improve the translation quality by more than 3.7 BLEU points, over a strong baseline, for this extremely low-resource scenario.
It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German--English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean-English dataset, surpassing previously reported results by 4 BLEU.
Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel corpora exist. As described in this paper, we propose a corpus augmentation method by segmenting long sentences in a corpus using back-translation and generating pseudo-parallel sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with Japanese-Chinese scientific paper excerpt corpus (ASPEC-JC) show that the method improves translation performance.
To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018). However, it is possible that an intelligent data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose an efficient algorithm, Target Conditioned Sampling (TCS), which first samples a target sentence, and then conditionally samples its source sentence. Experiments show that TCS brings significant gains of up to 2 BLEU on three of four languages we test, with minimal training overhead.