We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillation are widely-used, their interaction remains little understood. Our large-scale empirical results in machine translation (on three language pairs with three domains each) suggest distilling twice for best performance: once using general-domain data and again using in-domain data with an adapted teacher.
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Neural machine translation on low-resource language is challenging due to the lack of bilingual sentence pairs. Previous works usually solve the low-resource translation problem with knowledge transfer in a multilingual setting. In this paper, we propose the concept of Language Graph and further design a novel graph distillation algorithm that boosts the accuracy of low-resource translations in the graph with forward and backward knowledge distillation. Preliminary experiments on the TED talks multilingual dataset demonstrate the effectiveness of our proposed method. Specifically, we improve t…
Institute of Automation, CAS（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Fanyu AI Research, Beijing Fanyu Technology Ltd.（北京凡语科技有限公司凡语人工智能研究院）
A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavailable. In this scenario, the current methods suffer heavily from catastrophic forgetting (CF). To alleviate the CF, we investigate knowledge distillation based life-long learning methods. Specifically, in one-tomany scenario, we propose a multilingual distillation method to make the new model (student) jointly learn multilingual output from old model (teacher) and new task. In many-to one scenario, we find that direct…
University of Maryland（马里兰大学）；Microsoft Research Asia（微软亚洲研究院）
While non-autoregressive (NAR) models are showing great promise for machine translation, their use is limited by their dependence on knowledge distillation from autoregressive models. To address this issue, we seek to understand why distillation is so effective. Prior work suggests that distilled training data is less complex than manual translations. Based on experiments with the Levenshtein Transformer and the Mask-Predict NAR models on the WMT14 German-English task, this paper shows that different types of complexity have different impacts: while reducing lexical diversity and decreasing re…
Neural Machine Translation(NMT) models are usually trained via unidirectional decoder which corresponds to optimizing one-step-ahead prediction. However, this kind of unidirectional decoding framework may incline to focus on local structure rather than global coherence. To alleviate this problem, we propose a novel method, Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation(SBD-NMT). We deploy a backward decoder which can act as an effective regularization method to the forward decoder. By leveraging the backward decoder's information about the longer-term fut…
Microsoft Research Asia（微软亚洲研究院）；Zhejiang University（浙江大学）；Peking University（北京大学）
Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving. However, traditional multilingual translation usually yields inferior accuracy compared with the counterpart using individual models for each language pair, due to language diversity and model capacity limitations. In this paper, we propose a distillation-based approach to boost the accuracy of multilingual machine translation. Specifically, individual models are first trained and regarded as teachers, and then the…
IBM T.J. Watson Research Center（IBM T.J. Watson 研究中心）
Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a smaller model speeds up this process. We demonstrate how to transfer the translation quality of an ensemble and an oracle BLEU teacher network into a single NMT system. Further, we present translation improvements from a teacher network that has the same architecture and dimensions of the student network. As the training of the student model is still expensive…
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（脸书人工智能研究）
Non-autoregressive machine translation (NAT) systems predict a sequence of output tokens in parallel, achieving substantial improvements in generation speed compared to autoregressive models. Existing NAT models usually rely on the technique of knowledge distillation, which creates the training data from a pretrained autoregressive model for better performance. Knowledge distillation is empirically useful, leading to large gains in accuracy for NAT models, but the reason for this success has, as of yet, been unclear. In this paper, we first design systematic experiments to investigate why know…
Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；ByteDance Research（字节跳动研究院）；Damo Academy, Alibaba（阿里巴巴达摩院）
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Non-autoregressive neural machine translation (NAT) suffers from the multi-modality problem: the source sentence may have multiple correct translations, but the loss function is calculated only according to the reference sentence. Sequence-level knowledge distillation makes the target more deterministic by replacing the target with the output from an autoregressive model. However, the multi-modality problem in the distilled dataset is still nonnegligible. Furthermore, learning from a specific teacher limits the upper bound of the model capability, restricting the potential of NAT models. In th…
Continual Knowledge Distillation for Neural Machine Translation
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））
This paper explores augmenting monolingual data for knowledge distillation in neural machine translation. Source language monolingual text can be incorporated as a forward translation. Interestingly, we find the best way to incorporate target language monolingual text is to translate it to the source language and round-trip translate it back to the target language, resulting in a fully synthetic corpus. We find that combining monolingual data from both source and target languages yields better performance than a corpus twice as large only in one language. Moreover, experiments reveal that the …
Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学现代软件技术国家重点实验室）；ByteDance AI Lab（字节跳动人工智能实验室）；Collaborative Innovation Center of Novel Software Technology and Industrialization（现代软件技术与产业化协同创新中心）
Multi-Teacher Knowledge Distillation For Text Image Machine Translation
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Samsung Research China - Beijing（三星中国研究院（北京））；Zhongke Fanyu Technology Co., Ltd（中科凡语科技有限公司）
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, Peking University（北京大学数据科学中心）；The MOE Key Laboratory of Computational Linguistics, Peking University（北京大学计算语言学教育部重点实验室）
k-nearest-neighbor machine translation (NN-MT), proposed by Khandelwal et al. (2021), has achieved many state-of-the-art results in machine translation tasks. Although effective, NN-MT requires conducting NN searches through the large datastore for each decoding step during inference, prohibitively increasing the decoding cost and thus leading to the difficulty for the deployment in real-world applications. In this paper, we propose to move the time-consuming NN search forward to the preprocessing phase, and then introduce Nearest Neighbor Knowledge Distillation (NN-KD) that trains the base NM…
Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train smaller models? We test the common hypothesis that SLKD addresses a capacity deficiency in students by "simplifying" noisy data points and find it unlikely in our case. Models trained on concatenations of original and "simplified" datasets generalize just as well as baseline SLKD. We then propose an alternative hypothesis under the lens of data augmentation and re…
University of Sheffield（谢菲尔德大学）；Imperial College London（帝国理工学院）
Previous work on multimodal machine translation has shown that visual information is only needed in very specific cases, for example in the presence of ambiguous words where the textual context is not sufficient. As a consequence, models tend to learn to ignore this information. We propose a translate-and-refine approach to this problem where images are only used by a second stage decoder. This approach is trained jointly to generate a good first draft translation and to improve over this draft by (i) making better use of the target language textual context (both left and right-side contexts) …
Institute of Formal and Applied Linguistics, Charles University（查尔斯大学形式与应用语言学研究所）
In most of neural machine translation distillation or stealing scenarios, the goal is to preserve the performance of the target model (teacher). The highest-scoring hypothesis of the teacher model is commonly used to train a new model (student). If reference translations are also available, then better hypotheses (with respect to the references) can be upsampled and poor hypotheses either removed or undersampled. This paper explores the importance sampling method landscape (pruning, hypothesis upsampling and undersampling, deduplication and their combination) with English to Czech and English …
NTT Communication Science Laboratories（NTT通信科学实验室）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model. However, a NAT model often outputs shorter sentences than an AT model. In this work, we propose sequence-level knowledge distillation (SKD) using perturbed length-aware positional encoding and apply it to a student model, the Levenshtein Transformer. Our method outperformed a standard Levenshtein Transformer by 2.5 points in bilingual evaluation understudy (BLEU) at maximum in a WMT14 German to English translation. …
Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring teacher model's knowledge on each training sample. However, previous work rarely discusses the different impacts and connections among these samples, which serve as the medium for transferring teacher knowledge. In this paper, we design a novel protocol that can effectively analyze the different impacts of samples by comparing various samples' partitions. Based…
Nanyang Technological University（南洋理工大学）；Salesforce Research Asia（赛富时亚洲研究院）
Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently. Crucially, iterative back-translation and denoising auto-encoding for language modeling provide data diversity to train the UMT systems. However, the gains from these diversification processes has seemed to plateau. We introduce a novel component to the standard UMT framework called Cross-model Back-translated Distillation (CBD), that is aimed to induce another level of data diversification that exi…
Huawei Translation Services Center（华为翻译服务中心）；The University of Melbourne（墨尔本大学）
Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performing worse on raw data, most NAT models are trained as student models on distilled data generated by AT teacher models, which is known as sequence-level Knowledge Distillation. An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the…
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
Nilekani Centre at AI4Bharat（AI4Bharat的Nilekani中心）；Indian Institute of Technology（印度理工学院）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Engineering Science and Technology Shibpur（Shibpur的印度工程科学与技术学院）
Soochow University（苏州大学）；The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯AI实验室）
Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine Translation (AT) knowledge to NAT models, e.g., with knowledge distillation. In this work, we hypothesize and empirically verify that AT and NAT encoders capture different linguistic properties of source sentences. Therefore, we propose to adopt Multi-Task learning to transfer the AT knowledge to NAT models through encoder sharing. Specifically, we take the AT model…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
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 withou…
Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages
Center For Artificial Intelligence and Data Science, University of Würzburg（维尔茨堡大学人工智能与数据科学中心）；IESEG School of Management（IESEG管理学院）；KU Leuven（鲁汶大学）；Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）
Recent model pruning methods have demonstrated the ability to remove redundant parameters without sacrificing model performance. Common methods remove redundant parameters according to the parameter sensitivity, a gradient-based measure reflecting the contribution of the parameters. In this paper, however, we argue that redundant parameters can be trained to make beneficial contributions. We first highlight the large sensitivity (contribution) gap among high-sensitivity and low-sensitivity parameters and show that the model generalization performance can be significantly improved after balanci…
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However, there is still a significant performance gap between NMT and SiMT. In this work, we propose to leverage monolingual data to improve SiMT, which trains a SiMT student on the combination of bilingual data and external monolingual data distilled by Seq-KD. Preliminary experiments on En-Zh and En-Ja news domain corpora demonstrate that monolingual data can significantly improve translation quality (e.g., +3.15 BLEU on En-Zh…
Recent state-of-the-art approaches to summarization utilize large pre-trained Transformer models. Distilling these models to smaller student models has become critically important for practical use; however there are many different distillation methods proposed by the NLP literature. Recent work on distilling BERT for classification and regression tasks shows strong performance using direct knowledge distillation. Alternatively, machine translation practitioners distill using pseudo-labeling, where a small model is trained on the translations of a larger model. A third, simpler approach is to …
Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters. Self-supervised learning (SSL) approaches that leverage large quantities of monolingual data (where parallel data is unavailable) have shown promise by improving translation performance as complementary tasks to the MMT task. However, jointly optimizing SSL and MMT tasks is even more challenging. In this work, we first investigate how to utilize intra-distillation…
University of British Columbia（不列颠哥伦比亚大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain most of the parameters for language models and about a third for machine translation systems. In this paper, we propose Distilled Embedding, an (input/output) embedding compression method based on low-rank matrix decomposition and knowledge distillation. First, we initialize the weights of our decomposed matrices by learning to reconstruct the full pre-traine…
Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human post-editing workflows in Computer Assisted Translation (CAT). With Neural Machine Translation (NMT), we introduce a new notion of domain adaptation that we call "specialization" and which is showing promising results both in the learning speed and in adaptation accuracy. In this paper, we propose to explore this approach under several perspectives.
Shanghai University of Finance and Economics（上海财经大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the syntactic structure difference and simultaneity requirements. In this paper, we propose a general framework for adapting neural machine translation to translate simultaneously. Our framework contains two parts: prefix translation that utilizes a consecutive NMT model to translate source prefixes and a stopping criterion that determines when to stop the prefix translation. Experiment…
Northeastern University（东北大学）；The Chinese University of Hong Kong（香港中文大学）；NiuTrans Research（小牛翻译研究院）
Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest the effectiveness of transferring model parameters. Inspired by this, we investigate methods of model acceleration and compression in another line of research. We propose Weight Distillation to transfer the knowledge in the large network parameters through a parameter generator. Our experiments on WMT16 En-Ro, NIST12 Zh-En, and WMT14 En-De machine translation tasks show that we…
Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive machine translation sacrifice a lot of accuracy for data efficiency, and largely fail in creating a usable dialogue agent. We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i.e. zero-shot) or a small training set (i.e. few-shot).…
We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first use the zero-shot translation ability of large pre-trained language models to generate translations for a small set of unlabeled sentences. We then amplify these zero-shot translations by using them as few-shot demonstrations for sampling a larger synthetic dataset. This dataset is distilled by discarding the few-shot demonstrations and then fine-tuning. Durin…
One challenge of machine translation is how to quickly adapt to unseen domains in face of surging events like COVID-19, in which case timely and accurate translation of in-domain information into multiple languages is critical but little parallel data is available yet. In this paper, we propose an approach that enables rapid domain adaptation from the perspective of unsupervised translation. Our proposed approach only requires in-domain monolingual data and can be quickly applied to a preexisting translation system trained on general domain, reaching significant gains on in-domain translation …
Kazan Federal University（喀山联邦大学）；Heidelberg University（海德堡大学）
The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive learning of NMT by adaptation to human post-edits has so far been confined to simulation experiments. We present the first user study on online adaptation of NMT to user post-edits in the domain of patent translation. Our study involves 29 human subjects (translation students) whose post-editing effort and translation quality were measured on about 4,500 interactions of a human…
Northeastern University（东北大学）；School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；NLP Lab, School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院自然语言处理实验室）
This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including English$\leftrightarrow$$\{$Chinese, Japanese, Russian, Icelandic$\}$ and English$\rightarrow$Hausa tasks. Our primary systems are built on several effective variants of Transformer, e.g., Transformer-DLCL, ODE-Transformer. We also utilize back-translation, knowledge distillation, post-ensemble, and iterative fine-tuning techniques to enhance the model performance further.
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translation by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approa…
University of Luxembourg（卢森堡大学）；Banque BGL BNP Paribas（法国巴黎银行卢森堡BGL银行）
Natural language processing of Low-Resource Languages (LRL) is often challenged by the lack of data. Therefore, achieving accurate machine translation (MT) in a low-resource environment is a real problem that requires practical solutions. Research in multilingual models have shown that some LRLs can be handled with such models. However, their large size and computational needs make their use in constrained environments (e.g., mobile/IoT devices or limited/old servers) impractical. In this paper, we address this problem by leveraging the power of large multilingual MT models using knowledge dis…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；AppTek
Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques to transfer knowledge is knowledge distillation. In this paper, we compare the different solutions to distill knowledge in a sequence-to-sequence task like ST. Moreover, we analyze eventual drawbacks of this approach and how to alleviate them maintaining the benefits in terms of translation quality.
Institute for Datability Science（数据智能科学研究所）；Osaka University（大阪大学）
Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In thi…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；Baidu Inc.（百度公司）
End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-end ST models have advantages of lower latency, smaller model size and less error propagation. However, the combination of speech recognition and text translation in one model is more difficult than each of these two tasks. In this paper, we propose a knowledge distillation approach to improve ST model by transferring the knowledge from text translation model. Specifically, we f…
Harbin Institute of Technology（哈尔滨工业大学）；National Institute of Information and Communications Technology (NICT)（信息通信研究机构（NICT））
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time. That is, research on multilingual UNMT has been limited. In this paper, we empirically introduce a simple method to translate between thirteen languages using a single encoder and a single decoder, making use of multilingual data to improve UNMT for all language pairs. On the basis of the empirical findings, we propose two knowledge di…
