Knowledge distillation (KD) is essential for training non-autoregressive translation (NAT) models by reducing the complexity of the raw data with an autoregressive teacher model. In this study, we empirically show that as a side effect of this training, the lexical choice errors on low-frequency words are propagated to the NAT model from the teacher model. To alleviate this problem, we propose to expose the raw data to NAT models to restore the useful information of low-frequency words, which are missed in the distilled data. To this end, we introduce an extra Kullback-Leibler divergence term derived by comparing the lexical choice of NAT model and that embedded in the raw data. Experimental results across language pairs and model architectures demonstrate the effectiveness and universality of the proposed approach. Extensive analyses confirm our claim that our approach improves performance by reducing the lexical choice errors on low-frequency words. Encouragingly, our approach pushes the SOTA NAT performance on the WMT14 English-German and WMT16 Romanian-English datasets up to 27.8 and 33.8 BLEU points, respectively. The source code will be released.
We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than word and morpheme-level pivot models. It is also highly competitive with the best direct translation model, which is encouraging as no direct source-target training corpus is used. We also show that combining multiple related language pivot models can rival a direct translation model. Thus, the use of subwords as translation units coupled with multiple related pivot languages …
Beihang University（北京航空航天大学）；Xiaomi AI Lab（小米人工智能实验室）；Peking University（北京大学）；Chinese Academy of Sciences（中国科学院）
Non-autoregressive models generate target words in a parallel way, which achieve a faster decoding speed but at the sacrifice of translation accuracy. To remedy a flawed translation by non-autoregressive models, a promising approach is to train a conditional masked translation model (CMTM), and refine the generated results within several iterations. Unfortunately, such approach hardly considers the \textit{sequential dependency} among target words, which inevitably results in a translation degradation. Hence, instead of solely training a Transformer-based CMTM, we propose a Self-Review Mechani…
The University of Sydney（悉尼大学）；Tencent AI Lab（腾讯人工智能实验室）；University of Macau（澳门大学）；JD Explore Academy, JD.com（京东探索研究院）
Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original data, leading to more errors on predicting low-frequency words. To alleviate the problem, we directly expose the raw data into NAT by leveraging pretraining. By analyzing directed alignments, we found that KD makes low-frequency source words aligned with targets more deterministically but fails to align sufficient low-frequency words from target to source. Accordingly,…
However, current autoregressive approaches suffer from high latency. In this paper, we focus on non-autoregressive translation (NAT) for this problem for its efficiency advantage. We identify that current constrained NAT models, which are based on iterative editing, do not handle low-frequency constraints well. To this end, we propose a plug-in algorithm for this line of work, i.e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints. Experiments on the general and domain datasets show that our model impro…
University of St Andrews（圣安德鲁斯大学）；School of Computer Science（计算机科学学院）
By using a trigram model and fine-tuning a pretrained BERT model for sequence classification, we show that machine translation and human translation can be classified with an accuracy above chance level, which suggests that machine translation and human translation are different in a systematic way. The classification accuracy of machine translation is much higher than of human translation. We show that this may be explained by the difference in lexical diversity between machine translation and human translation. If machine translation has independent patterns from human translation, automatic…
In this paper we describe some ways to utilize various lexical resources to improve the quality of statistical machine translation system. We have augmented the training corpus with various lexical resources such as IndoWordnet semantic relation set, function words, kridanta pairs and verb phrases etc. Our research on the usage of lexical resources mainly focused on two ways such as augmenting parallel corpus with more vocabulary and augmenting with various word forms. We have described case studies, evaluations and detailed error analysis for both Marathi to Hindi and Hindi to Marathi machine…
We explore two solutions to the problem of mistranslating rare words in neural machine translation. First, we argue that the standard output layer, which computes the inner product of a vector representing the context with all possible output word embeddings, rewards frequent words disproportionately, and we propose to fix the norms of both vectors to a constant value. Second, we integrate a simple lexical module which is jointly trained with the rest of the model. We evaluate our approaches on eight language pairs with data sizes ranging from 100k to 8M words, and achieve improvements of up t…
Rakuten Institute of Technology Singapore（新加坡乐天技术研究所）；Rakuten, Inc.（乐天株式会社）
This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be …
The paper presents a prototype lexicalist Machine Translation system (based on the so-called `Shake-and-Bake' approach of Whitelock (1992) consisting of an analysis component, a dynamic bilingual lexicon, and a generation component, and shows how it is applied to a range of MT problems. Multi-Lexeme translations are handled through bi-lexical rules which map bilingual lexical signs into new bilingual lexical signs. It is argued that much translation can be handled by equating translationally equivalent lists of lexical signs, either directly in the bilingual lexicon, or by deriving them throug…
Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatiz…
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the lexical- and high-level representations of the two languages. While cross-lingual pretraining works for similar languages with abundant corpora, it performs poorly in low-resource and distant languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language m…
Indian Institute of Technology (IIT) Bombay（印度理工学院孟买分校）
In this paper, we present our work on the creation of lexical resources for the Machine Translation between English and Hindi. We describes the development of phrase pair mappings for our experiments and the comparative performance evaluation between different trained models on top of the baseline Statistical Machine Translation system. We focused on augmenting the parallel corpus with more vocabulary as well as with various inflected forms by exploring different ways. We have augmented the training corpus with various lexical resources such as lexical words, synset words, function words and v…
Lexically cohesive translations preserve consistency in word choices in document-level translation. We employ a copy mechanism into a context-aware neural machine translation model to allow copying words from previous translation outputs. Different from previous context-aware neural machine translation models that handle all the discourse phenomena implicitly, our model explicitly addresses the lexical cohesion problem by boosting the probabilities to output words consistently. We conduct experiments on Japanese to English translation using an evaluation dataset for discourse translation. The …
This paper discusses the lexicographical concept of lexical functions and their potential exploitation in the development of a machine translation lexicon designed to handle collocations.
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Quan Cheng Laboratory（之江实验室）
Lexically constrained neural machine translation (NMT), which controls the generation of NMT models with pre-specified constraints, is important in many practical scenarios. Due to the representation gap between discrete constraints and continuous vectors in NMT models, most existing works choose to construct synthetic data or modify the decoding algorithm to impose lexical constraints, treating the NMT model as a black box. In this work, we propose to open this black box by directly integrating the constraints into NMT models. Specifically, we vectorize source and target constraints into cont…
Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario. Out-of-domain translations are often of poor quality and prone to hallucinations, due to exposure bias and the decoder acting as a language model. We adopt two approaches to alleviate this problem: lexical shortlisting restricted by IBM statistical alignments, and hypothesis re-ranking based on similarity. The methods are computationally cheap, widely known, but not extensively experimented on domain adaptation. We demonstrate success on low-resource out-of-domain test sets, however, the metho…
Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Lexically constrained decoding for machine translation has shown to be beneficial in previous studies. Unfortunately, constraints provided by users may contain mistakes in real-world situations. It is still an open question that how to manipulate these noisy constraints in such practical scenarios. We present a novel framework that treats constraints as external memories. In this soft manner, a mistaken constraint can be corrected. Experiments demonstrate that our approach can achieve substantial BLEU gains in handling noisy constraints. These results motivate us to apply the proposed approach…
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…
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position, instead of only one token, we predict a short sequence of tokens in an autoregressive way. We further design an efficient merging algorithm to align and merge the out-put pieces into one final output sequence. We integrate LAT into the conditional masked language model (CMLM; Ghazvininejad et al.,2019) and similarly adopt iterative decoding. Empirical resul…
Bytedance AI Lab（字节跳动人工智能实验室）；University of California Santa Barbara（加利福尼亚大学圣巴巴拉分校）
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation system using the Glancing Transformer, which enables fast and accurate parallel decoding in contrast to the currently prevailing autoregressive models. To the best of our knowledge, this is the first parallel translation system that can be scaled to such a practical scenario like WMT competition. More importantly, our parallel translation system achieves the best BLEU score (35.0) on German->English translation task…
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…
Yandex（扬达克斯）；University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）；University of Zurich（苏黎世大学）
Though machine translation errors caused by the lack of context beyond one sentence have long been acknowledged, the development of context-aware NMT systems is hampered by several problems. Firstly, standard metrics are not sensitive to improvements in consistency in document-level translations. Secondly, previous work on context-aware NMT assumed that the sentence-aligned parallel data consisted of complete documents while in most practical scenarios such document-level data constitutes only a fraction of the available parallel data. To address the first issue, we perform a human study on an…
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…
Charles University（查理大学）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate paraphrases from such a model using standard beam search produces trivial copies or near copies. We introduce a simple paraphrase generation algorithm which discourages the production of n-grams that are present in the input. Our approach enables paraphrase generation in many languages from a single multilingual NMT model. Furthermore, the amount of lexical diversity…
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…
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）；University of Zurich（苏黎世大学）
Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite neural machine translation being de-facto standard, it is still not clear how NMT models acquire different competences over the course of training, and how this mirrors the different models in traditional SMT. In this work, we look at the competences related to three core SMT components and find that during training, NMT first focuses on learning target-side lang…
The interest in statistical machine translation systems increases currently due to political and social events in the world. A proposed Statistical Machine Translation (SMT) based model that can be used to translate a sentence from the source Language (English) to the target language (Arabic) automatically through efficiently incorporating different statistical and Natural Language Processing (NLP) models such as language model, alignment model, phrase based model, reordering model, and translation model. These models are combined to enhance the performance of statistical machine translation (…
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…
Indian Institute of Technology (IIT) Bombay（印度理工学院孟买分校）
Lack of proper linguistic resources is the major challenges faced by the Machine Translation system developments when dealing with the resource poor languages. In this paper, we describe effective ways to utilize the lexical resources to improve the quality of statistical machine translation. Our research on the usage of lexical resources mainly focused on two ways, such as; augmenting the parallel corpus with more vocabulary and to provide various word forms. We have augmented the training corpus with various lexical resources such as lexical words, function words, kridanta pairs and verb phr…
Non-autoregressive translation (NAT) model achieves a much faster inference speed than the autoregressive translation (AT) model because it can simultaneously predict all tokens during inference. However, its translation quality suffers from degradation compared to AT. And existing NAT methods only focus on improving the NAT model's performance but do not fully utilize it. In this paper, we propose a simple but effective method called "Candidate Soups," which can obtain high-quality translations while maintaining the inference speed of NAT models. Unlike previous approaches that pick the indiv…
Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）
To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL). However, multilingual data has been found more beneficial for NMT models that translate from the LRL to a target language than the ones that translate into the LRLs. In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate \emph{into} the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft …
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…
In this paper we describe an algorithm for aligning sentences with their translations in a bilingual corpus using lexical information of the languages. Existing efficient algorithms ignore word identities and consider only the sentence lengths (Brown, 1991; Gale and Church, 1993). For a sentence in the source language text, the proposed algorithm picks the most likely translation from the target language text using lexical information and certain heuristics. It does not do statistical analysis using sentence lengths. The algorithm is language independent. It also aids in detecting addition and…
We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance. CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Kendall's tau distance is introduced as the quantitative metric, and gradient-based visualization provides an intuitive way to take a closer look into the model. Our analysis shows that transformer encoders have the ability to change…
Indian Institute of Technology (IIT) Bombay（印度理工学院孟买分校）
Being less resource languages, Indian-Indian and English-Indian language MT system developments faces the difficulty to translate various lexical phenomena. In this paper, we present our work on a comparative study of 440 phrase-based statistical trained models for 110 language pairs across 11 Indian languages. We have developed 110 baseline Statistical Machine Translation systems. Then we have augmented the training corpus with Indowordnet synset word entries of lexical database and further trained 110 models on top of the baseline system. We have done a detailed performance comparison using …
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…
Shanghai Jiao Tong University（上海交通大学）；Centre National de la Recherche Scientifique（法国国家科学研究中心）；National Institute of Information and Communications Technology（信息通信研究机构）
Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information. In this paper, we propose a latent bilingual sense unit (Bilingual Sense Clique, BSC), which is derived from a maximum complete sub-graph of pointwise mutual information based graph over bilingual corpus. In this way, we treat source and target words equally and a separated bilingual projection processing that have to be used in most existing works is not necessary any more. Several dimension reduction methods are evaluated to summarize the BSC-word relationship. The pro…
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）；University of Zurich（苏黎世大学）
The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and propagated through a deep network of hidden layers. We argue that the need to represent and propagate lexical features in each layer limits the model's capacity for learning and representing other information relevant to the task. To alleviate this bottleneck, we introduce gated shortcut connections between the embedding layer and each subsequent layer within the en…
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 …
