State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in inference since we cannot generate multiple tokens in each sentence in parallel. We propose an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts. The DisCo transformer is trained to predict every output token given an arbitrary subset of the other reference tokens. We also develop the parallel easy-first inference algorithm, which iteratively refines every token in parallel and reduces the number of required iterations. Our extensive experiments on 7 translation directions with varying data sizes demonstrate that our model achieves competitive, if not better, performance compared to the state of the art in non-autoregressive machine translation while significantly reducing decoding time on average. Our code is available at https://github.com/facebookresearch/DisCo.
Charles University（查理大学）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in parallel. We present a novel non-autoregressive architecture based on connectionist temporal classification and evaluate it on the task of neural machine translation. Unlike other non-autoregressive methods which operate in several steps, our model can be trained end-to-end. We conduct experiments on the WMT English-Romanian and English-German datasets. Our models a…
University of Washington（华盛顿大学）；Facebook AI（脸书人工智能）；Allen Institute for AI（艾伦人工智能研究所）
Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where generation is sequential, the former allows generation to be parallelized across target token positions. Some of the latest non-autoregressive models have achieved impressive translation quality-speed tradeoffs compared to autoregressive baselines. In this work, we reexamine this tradeoff and argue that autoregressive baselines can be substantially sped up witho…
Alibaba Group（阿里巴巴集团）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation --- the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus is able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show tha…
Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compared to autoregressive neural machine translation models due to the enormous decoding space. To address this problem, we propose a novel NAT framework named ReorderNAT which explicitly models the reordering information in the decoding procedure. We further introduce deterministic and non-deterministic decoding strategies that utilize reordering information to narrow the decoding…
How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent non-autoregressive translation models speed up the inference, but their quality is still inferior. In this work, we propose DSLP, a highly efficient and high-performance model for machine translation. The key insight is to train a non-autoregressive Transformer with Deep Supervision and feed additional Layer-wise Predictions. We conducted extensive experiments on …
Peking University（北京大学）；Beijing Institute of Big Data Research（北京大数据研究院）；Tencent CSIG（腾讯云与智慧产业事业群）
Non-autoregressive translation models (NAT) have achieved impressive inference speedup. A potential issue of the existing NAT algorithms, however, is that the decoding is conducted in parallel, without directly considering previous context. In this paper, we propose an imitation learning framework for non-autoregressive machine translation, which still enjoys the fast translation speed but gives comparable translation performance compared to its auto-regressive counterpart. We conduct experiments on the IWSLT16, WMT14 and WMT16 datasets. Our proposed model achieves a significant speedup over t…
Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem well suited to translate with a Translation Memory (TM). This is the scenario considered here. We first analyze the vanilla LevT model and explain why it does not do well in this setting. We then propose a new variant, TM-LevT, and show how to effectively train this model. By modifying the data presentation and introducing an extra deletion operation, we obt…
Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel. However, such independent predictions prevent NATs from capturing the dependencies between the tokens for generating multiple possible translations. In this paper, we propose Directed Acyclic Transfomer (DA-Transformer), which represents the hidden states in a Directed Acyclic Graph (DAG), where each path of the DAG corresponds to a specific translation. The whole DAG simultaneously captures multiple translations and facilitates fast predictions in a non-autoregressive fashion…
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. …
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）
University of Chinese Academy of Sciences（中国科学院大学）
Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously. Despite its high efficiency, NAT usually suffers from two kinds of translation errors: over-translation (e.g. repeated tokens) and under-translation (e.g. missing translations), which eventually limits the translation quality. In this paper, we argue that these issues of NAT can be addressed through coverage modeling, which has been proved to be useful in autoregressive decoding. We propose a novel Coverage-NAT to model the coverage information directly by a t…
Tencent AI Lab（腾讯人工智能实验室）；Zhejiang University（浙江大学）；Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption. This assumption is further strengthened by cross-entropy loss, which encourages a strict match between the hypothesis and the reference token by token. To alleviate this issue, we propose multi-granularity optimization for NAT, which collects model behaviors on translation segments of various granularities and integrates feedback for backpropagation. Experiments on four WMT benchmarks show that the proposed method significantly outperforms the bas…
Pattern Recognition Center, WeChat AI, Tencent Inc.（腾讯公司微信AI模式识别中心）
Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably suffers from the multi-modality problem: the target tokens may be provided by different possible translations, often causing token repetitions or missing. To alleviate this problem, we propose a novel semi-autoregressive model RecoverSAT in this work, which generates a translation as a sequence of segments. The segments are generated simultaneously while each se…
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…
Shanghai Jiao Tong University（上海交通大学）；ByteDance AI Lab（字节跳动人工智能实验室）；Nanjing University（南京大学）
Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup. We propose the Glancing Language Model (GLM), a method to learn word interdependency for single-pass parallel generation models. With GLM, we develop Glancing Transformer (GLAT) for machine translation. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8-15 times speedu…
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 models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Expe…
Pattern Recognition Center, WeChat AI, Tencent Inc.（腾讯公司微信人工智能模式识别中心）
Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when the NAT output is closer to other translations. In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. As we train NAT based on the rephraser output rather than the reference sentence, the rephraser output should fit well with the NAT output and not …
University of Maryland（马里兰大学）；Google Research（谷歌研究院）
Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficient alternative to AR inference. However, while AR translation is often implemented using multilingual models that benefit from transfer between languages and from improved serving efficiency, multilingual NAR models remain relatively unexplored. Taking Connectionist Temporal Classification (CTC) as an example NAR model and Imputer as a semi-NAR model, we present a comprehensive empirical study of multilingual NAR. We…
Charles University（查理大学）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with connectionist temporal classification (CTC) by employing additional features in the scoring model used during beam search decoding. Since the beam search decoding in our model only requires to run the network in a single forward pass, the decoding speed is still notably higher than in standard AR models. We train models for three language pairs: German, Czech, an…
Singapore Management University（新加坡管理大学）；Tencent AI Lab（腾讯人工智能实验室）
Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy loss. Starting from the intuition that reordering generally occurs between phrases, we extend oaxe by only allowing reordering between ngram phrases and still requiring a strict match of word order within the phrases. Extensive experiments on NAT benchmarks across language pairs and data scales demonstrate the effectiveness and universality of our approach. %Further analyses show …
eBay Inc.（eBay公司）；Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany（德国亚琛工业大学人类语言技术与模式识别小组）
Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an individual system is trained for both sub-tasks. However, these models have no connection during training, and the source-pivot model is not optimized to produce the best translation for the source-target task. In this work, we propose to train a pivot-based NMT system with the reinforcement learning (RL) approach, which has been investigated for various text …
Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院人工智能研究院）
Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality trade-off. For one thing, fully NAT models with efficient inference perform inferior to their autoregressive counterparts. For another, iterative NAT models can, though, achieve comparable performance while diminishing the advantage of speed. In this paper, we propose RenewNAT, a flexible framework with high efficiency and effectiveness, to incorporate the m…
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 translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent alignment models relax the explicit alignment by marginalizing out all monotonic latent alignments with the CTC loss. However, they cannot handle non-monotonic alignments, which is non-negligible as there is typically global word reordering in machine translation. In this work, we explore non-monotonic latent alignments for NAT. We extend the alignment space t…
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…
University of Edinburgh（爱丁堡大学）；Charles University（查理大学）
Efficient machine translation models are commercially important as they can increase inference speeds, and reduce costs and carbon emissions. Recently, there has been much interest in non-autoregressive (NAR) models, which promise faster translation. In parallel to the research on NAR models, there have been successful attempts to create optimized autoregressive models as part of the WMT shared task on efficient translation. In this paper, we point out flaws in the evaluation methodology present in the literature on NAR models and we provide a fair comparison between a state-of-the-art NAR mod…
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…
Facebook AI Research（脸书人工智能研究院）；Carnegie Mellon University（卡内基梅隆大学）
Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the Transformer baseline. In this work, we target on closing the performance gap while maintaining the latency advantage. We first inspect the fundamental issues of fully NAT models, and adopt dependency reduction in the learning space of output tokens as the basic guidance. Then, we revisit methods in four different aspects that have been proven effective for i…
This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a simple CTC model can achieve state-of-the-art for single-step non-autoregressive machine translation, contrary to what prior work indicates. In addition, we adapt the Imputer model for non-autoregressive machine translation and demonstrate that Imputer with just 4 generation steps can match the performance of an autoregressive Transformer baseline. Our latent alignment models are …
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…
We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et al., 2020), we train an inference network to approximate the gradient of the marginal log probability of the target sentence, using only the latent variable as input. This allows us to use gradient-based optimization to find the target sentence at inference time that approximately maximizes its marginal probability. As each refinement step only involves computation in …
RoyalFlush AI Research Institute（同花顺人工智能研究院）；Zhejiang University（浙江大学）
This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every $k$ tokens, $k>1$) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；University of Chicago（芝加哥大学）；New York University（纽约大学）
We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference network (Tu and Gimpel, 2018) trained to minimize the autoregressive teacher energy. This contrasts with the popular approach of training a non-autoregressive model on a distilled corpus consisting of the beam-searched outputs of such a teacher model. Our approach, which we call ENGINE (ENerGy-based Inference NEtworks), achieves state-of-the-art non-autoregressive results on the I…
Cranberry-Lemon University（蔓越莓柠檬大学）；University of the Witwatersrand（威特沃特斯兰德大学）
In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device setting than autoregressive translation (AT). Inspired by it, we attempt to investigate how to combine the strengths of autoregressive and non-autoregressive translation paradigms better. To this end, we demonstrate through synthetic experiments that prompting a small number of AT's predictions can promote one-shot non-autoregressive translation to achieve the e…
Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
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）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency modeling among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performanc…
Beihang University（北京航空航天大学）；Chinese Academy of Sciences（中国科学院）
Conditional masked language models (CMLM) have shown impressive progress in non-autoregressive machine translation (NAT). They learn the conditional translation model by predicting the random masked subset in the target sentence. Based on the CMLM framework, we introduce Multi-view Subset Regularization (MvSR), a novel regularization method to improve the performance of the NAT model. Specifically, MvSR consists of two parts: (1) \textit{shared mask consistency}: we forward the same target with different mask strategies, and encourage the predictions of shared mask positions to be consistent w…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Huazhong University of Science and Technology（华中科技大学）
The non-autoregressive models have boosted the efficiency of neural machine translation through parallelized decoding at the cost of effectiveness when comparing with the autoregressive counterparts. In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance. However, these structures are rarely considered in the existing non-autoregressive models. Inspired by this intuition, we propose to incorporate the explicit syntactic and semantic structures of languages into a n…
College of Information and Computer Sciences（信息与计算机科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the decoder computations at training time, inference still proceeds sequentially. Recent developments in non- and semi- autoregressive decoding produce multiple tokens per time step independently of the others, which improves inference speed but deteriorates translation quality. In this work, we propose the syntactically supervised Transformer (SynST), which first…
The Blavatnik School of Computer Science（布拉瓦特尼克计算机科学学院）；Tel Aviv University（特拉维夫大学）
Latent alignment objectives such as CTC and AXE significantly improve non-autoregressive machine translation models. Can they improve autoregressive models as well? We explore the possibility of training autoregressive machine translation models with latent alignment objectives, and observe that, in practice, this approach results in degenerate models. We provide a theoretical explanation for these empirical results, and prove that latent alignment objectives are incompatible with teacher forcing.
Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their translation quality still tends to be inferior to their autoregressive counterparts due to several issues involving output token interdependence. In this work, we take a step back and revisit several techniques that have been proposed for improving non-autoregressive translation models and compare their combined translation quality and speed implications under thi…
Zhejiang University（浙江大学）；Microsoft Research Asia（微软亚洲研究院）
It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the "multi-modality problem", including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenge to the standard cross entropy (XE) loss in NAT and is under studied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-ra…
The University of Tokyo（东京大学）；New York University（纽约大学）；Facebook AI Research（脸书人工智能研究院）
Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we propose LaNMT, a latent-variable non-autoregressive model with continuous latent variables and deterministic inference procedure. In contrast to existing approaches, we use a deterministic inference algorithm to find the target sequence that maximizes the lowerbound to the log-probability. During inference, the length of translation automatically adapts itself. Ou…
Zhejiang University（浙江大学）；Westlake University（西湖大学）；Nanyang Technological University（南洋理工大学）；Tsinghua University（清华大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingual corpora to improve the NAR model's performance, with the goal of transferring the AR model's generalization ability while preventing overfitting. On top of a strong NAR baseline, our experimental results on the WMT14 En-De and WMT16 En-Ro news translation tasks confirm that monolingual data augmentation consistently improves the performance of the NAR model to approach the teacher AR model's performance, yields com…
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）；Tencent Inc（腾讯公司）
Non-Autoregressive Neural Machine Translation (NAT) achieves significant decoding speedup through generating target words independently and simultaneously. However, in the context of non-autoregressive translation, the word-level cross-entropy loss cannot model the target-side sequential dependency properly, leading to its weak correlation with the translation quality. As a result, NAT tends to generate influent translations with over-translation and under-translation errors. In this paper, we propose to train NAT to minimize the Bag-of-Ngrams (BoN) difference between the model output and the …
Recently, simultaneous translation has gathered a lot of attention since it enables compelling applications such as subtitle translation for a live event or real-time video-call translation. Some of these translation applications allow editing of partial translation giving rise to re-translation approaches. The current re-translation approaches are based on autoregressive sequence generation models (ReTA), which generate tar-get tokens in the (partial) translation sequentially. The multiple re-translations with sequential generation inReTAmodelslead to an increased inference time gap between t…
Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency. Non-AutoRegressive Translation (NART) models were proposed to reduce the inference time, but could only achieve inferior translation accuracy. In this paper, we proposed a novel approach to leveraging the hints from hidden states and word alignments to help the training of NART models. The results achieve significant improvement over previous NART models for the WMT14 En-De and De-En dat…
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）
Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clear what the best inference strategy is. We formulate masked inference as a factorization of conditional probabilities of partial sequences, show that this does not harm performance, and investigate a number of simple heuristics motivated by this perspective. We identify a thresholding strategy that has advantages over the standard "mask-predict" algorithm, and provide analyses o…
Salesforce Research（Salesforce研究院）；The University of Hong Kong（香港大学）
Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude lower latency during inference. Through knowledge distillation, the use of input token fertilities as a latent variable, and policy gradient fine-tuning, we achieve this at a cost of as little as 2.0 BLEU points relative to the autoregressive Transformer network used as a teacher. We demonstrate substantial cumulative improvements associated with each of th…
Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is more challenging due to the lack of autoregressive factors in the model. This difficultly is compounded during training with cross entropy loss, which can highly penalize small shifts in word order. In this paper, we propose aligned cross entropy (AXE) as an alternative loss function for training of non-autoregressive models. AXE uses a differentiable dynamic program to assign loss based on the best possible monotonic a…
Non-autoregressive Streaming Transformer for Simultaneous Translation
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）；Soochow University（苏州大学）
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Tencent Inc（腾讯公司）
Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information. Over-translation and under-translation errors often occur for the above reason, especially in the long sentence translation scenario. In this paper, we propose two approaches to retrieve the target sequential information for NAT to enhance its translation ability while preserving the fast-decoding property. Firstly, we propose a sequence-level training method based on a …
Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly modeling dependencies between outputs. In this paper, we introduce AligNART, which leverages full alignment information to explicitly reduce the modality of the target distribution. AligNART divides the machine translation task into $(i)$ alignment estimation and $(ii)$ translation with aligned decoder inputs, guiding the decoder to focus on simplified one-to-…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of the reasons hindering compositional generalization relates to representations being entangled. We propose an extension to sequence-to-sequence models which encourages disentanglement by adaptively re-encoding (at each time step) the source input. Specifically, we condition the source representations on the newly decoded target context which makes it easier for…
