Neural Machine Translation (NMT) models are sensitive to small perturbations in the input. Robustness to such perturbations is typically measured using translation quality metrics such as BLEU on the noisy input. This paper proposes additional metrics which measure the relative degradation and changes in translation when small perturbations are added to the input. We focus on a class of models employing subword regularization to address robustness and perform extensive evaluations of these models using the robustness measures proposed. Results show that our proposed metrics reveal a clear trend of improved robustness to perturbations when subword regularization methods are used.
Peking University（北京大学）；University of Edinburgh（爱丁堡大学）
Idiom translation is a challenging problem in machine translation because the meaning of idioms is non-compositional, and a literal (word-by-word) translation is likely to be wrong. In this paper, we focus on evaluating the quality of idiom translation of MT systems. We introduce a new evaluation method based on an idiom-specific blacklist of literal translations, based on the insight that the occurrence of any blacklisted words in the translation output indicates a likely translation error. We introduce a dataset, CIBB (Chinese Idioms Blacklists Bank), and perform an evaluation of a state-of-…
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）
Back translation (BT) has been widely used and become one of standard techniques for data augmentation in Neural Machine Translation (NMT), BT has proven to be helpful for improving the performance of translation effectively, especially for low-resource scenarios. While most works related to BT mainly focus on European languages, few of them study languages in other areas around the world. In this paper, we investigate the impacts of BT on Asia language translations between the extremely low-resource Chinese and Vietnamese language pair. We evaluate and compare the effects of different sizes o…
As generic machine translation (MT) quality has improved, the need for targeted benchmarks that explore fine-grained aspects of quality has increased. In particular, gender accuracy in translation can have implications in terms of output fluency, translation accuracy, and ethics. In this paper, we introduce MT-GenEval, a benchmark for evaluating gender accuracy in translation from English into eight widely-spoken languages. MT-GenEval complements existing benchmarks by providing realistic, gender-balanced, counterfactual data in eight language pairs where the gender of individuals is unambiguo…
Machine translation (MT) systems are now able to provide very accurate results for high resource language pairs. However, for many low resource languages, MT is still under active research. In this paper, we develop and share a dataset to automatically evaluate the quality of MT systems for Amharic. We compare two commercially available MT systems that support translation of Amharic to and from English to assess the current state of MT for Amharic. The BLEU score results show that the results for Amharic translation are promising but still low. We hope that this dataset will be useful to the r…
We study several methods for full or partial sharing of the decoder parameters of multilingual NMT models. We evaluate both fully supervised and zero-shot translation performance in 110 unique translation directions using only the WMT 2019 shared task parallel datasets for training. We use additional test sets and re-purpose evaluation methods recently used for unsupervised MT in order to evaluate zero-shot translation performance for language pairs where no gold-standard parallel data is available. To our knowledge, this is the largest evaluation of multi-lingual translation yet conducted in …
National Research Council Canada（加拿大国家研究委员会）；Google（谷歌）
Neural machine translation represents an exciting leap forward in translation quality. But what longstanding weaknesses does it resolve, and which remain? We address these questions with a challenge set approach to translation evaluation and error analysis. A challenge set consists of a small set of sentences, each hand-designed to probe a system's capacity to bridge a particular structural divergence between languages. To exemplify this approach, we present an English-French challenge set, and use it to analyze phrase-based and neural systems. The resulting analysis provides not only a more f…
University of Zurich（苏黎世大学）；University of Edinburgh（爱丁堡大学）
As machine translation (MT) metrics improve their correlation with human judgement every year, it is crucial to understand the limitations of such metrics at the segment level. Specifically, it is important to investigate metric behaviour when facing accuracy errors in MT because these can have dangerous consequences in certain contexts (e.g., legal, medical). We curate ACES, a translation accuracy challenge set, consisting of 68 phenomena ranging from simple perturbations at the word/character level to more complex errors based on discourse and real-world knowledge. We use ACES to evaluate a …
Neural Machine Translation models are sensitive to noise in the input texts, such as misspelled words and ungrammatical constructions. Existing robustness techniques generally fail when faced with unseen types of noise and their performance degrades on clean texts. In this paper, we focus on three types of realistic noise that are commonly generated by humans and introduce the idea of visual context to improve translation robustness for noisy texts. In addition, we describe a novel error correction training regime that can be used as an auxiliary task to further improve translation robustness.…
The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation performance on low resource languages hints at potential cross-lingual transfer capability for downstream tasks. In this paper, we evaluate the cross-lingual effectiveness of representations from the encoder of a massively multilingual NMT model on 5 downstream classification and sequence labeling tasks covering a diverse set of over 50 languages. We compare against a strong baseli…
Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The recently created Machine Translation on Noisy Text task corpus provides noisy-clean parallel data for a few language pairs, but this data is very limited in size and diversity. The state-of-the-art approaches are heavily dependent on large volumes of back-translated data. This paper has two main contributions: Firstly, we propose new data augmentation methods to e…
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
We present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT). Our approach uses two recent coreference resolution datasets composed of English sentences which cast participants into non-stereotypical gender roles (e.g., "The doctor asked the nurse to help her in the operation"). We devise an automatic gender bias evaluation method for eight target languages with grammatical gender, based on morphological analysis (e.g., the use of female inflection for the word "doctor"). Our analyses show that four popular industrial MT systems and two…
College of Natural Sciences（自然科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Department of Computer Science（计算机科学系）；San Jose State University（圣何塞州立大学）；Department of Linguistics（语言学系）；College of Information and Computer Sciences（信息与计算机科学学院）
Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93\% of the model translation…
NTT DOCOMO, INC.（NTT都科摩公司）；NTT Communication Science Laboratories, NTT Corporation（NTT集团通信科学实验室）
This paper describes NTT's submission to the WMT19 robustness task. This task mainly focuses on translating noisy text (e.g., posts on Twitter), which presents different difficulties from typical translation tasks such as news. Our submission combined techniques including utilization of a synthetic corpus, domain adaptation, and a placeholder mechanism, which significantly improved over the previous baseline. Experimental results revealed the placeholder mechanism, which temporarily replaces the non-standard tokens including emojis and emoticons with special placeholder tokens during translati…
Translating text that diverges from the training domain is a key challenge for machine translation. Domain robustness---the generalization of models to unseen test domains---is low for both statistical (SMT) and neural machine translation (NMT). In this paper, we study the performance of SMT and NMT models on out-of-domain test sets. We find that in unknown domains, SMT and NMT suffer from very different problems: SMT systems are mostly adequate but not fluent, while NMT systems are mostly fluent, but not adequate. For NMT, we identify such hallucinations (translations that are fluent but unre…
This paper describes the systems that we submitted to the WMT19 Machine Translation robustness task. This task aims to improve MT's robustness to noise found on social media, like informal language, spelling mistakes and other orthographic variations. The organizers provide parallel data extracted from a social media website in two language pairs: French-English and Japanese-English (in both translation directions). The goal is to obtain the best scores on unseen test sets from the same source, according to automatic metrics (BLEU) and human evaluation. We proposed one single and one ensemble …
We share a French-English parallel corpus of Foursquare restaurant reviews (https://europe.naverlabs.com/research/natural-language-processing/machine-translation-of-restaurant-reviews), and define a new task to encourage research on Neural Machine Translation robustness and domain adaptation, in a real-world scenario where better-quality MT would be greatly beneficial. We discuss the challenges of such user-generated content, and train good baseline models that build upon the latest techniques for MT robustness. We also perform an extensive evaluation (automatic and human) that shows significa…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the cl…
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Although, Chinese and Spanish are two of the most spoken languages in the world, not much research has been done in machine translation for this language pair. This paper focuses on investigating the state-of-the-art of Chinese-to-Spanish statistical machine translation (SMT), which nowadays is one of the most popular approaches to machine translation. For this purpose, we report details of the available parallel corpus which are Basic Traveller Expressions Corpus (BTEC), Holy Bible and United Nations (UN). Additionally, we conduct experimental work with the largest of these three corpora to e…
University of Zurich（苏黎世大学）；LIMSI, CNRS, Univ. Paris-Sud, Université Paris-Saclay（法国国家科学研究中心、巴黎第十一大学、巴黎萨克雷大学联合计算机科学与数学应用实验室）；University of Edinburgh（爱丁堡大学）
For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard automatic metrics, poorly adapted to evaluating discourse phenomena. In this article, we present hand-crafted, discourse test sets, designed to test the models' ability to exploit previous source and target sentences. We investigate the performance of recently proposed multi-encoder NMT models trained on subtitles for English to Fren…
University of Electronic Science and Technology of China（电子科技大学）；Tencent AI Lab（腾讯人工智能实验室）；Harbin Institute of Technology（哈尔滨工业大学）
Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods. Word Alignment Error Rate can be used as such a metric that matches human understanding, however, it can not measure explanation methods on those target words that are not aligned to any source word. This paper thereby makes an initial attempt to evaluate explanation methods from an alternative viewpoint. To this end, it proposes a principled metric based on fidelity in regard to the predictive behavior of the NMT model. As the exact co…
Monash University（莫纳什大学）；Oracle Corp.（甲骨文公司）；University of Cambridge（剑桥大学）；The University of Melbourne（墨尔本大学）
Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on real interpretation data. To illustrate this argument, we propose an interpretation test set and conduct a realistic evaluation of SiMT trained on offline translations. Our results, on our test set along with 3 existing smaller scale language pairs, highlight the difference of up-to 13.83 BLEU score when SiMT models are evaluated on translation vs interpretation data. In the absence of interpretation training data, we…
CNRS（法国国家科学研究中心）；LISN（计算机科学实验室）；Université Paris-Saclay（巴黎萨克雷大学）；Inria Paris（法国国家信息与自动化研究所巴黎中心）；Université de Paris（巴黎大学）；LLF（形式语言学实验室）
This work explores the capacities of character-based Neural Machine Translation to translate noisy User-Generated Content (UGC) with a strong focus on exploring the limits of such approaches to handle productive UGC phenomena, which almost by definition, cannot be seen at training time. Within a strict zero-shot scenario, we first study the detrimental impact on translation performance of various user-generated content phenomena on a small annotated dataset we developed, and then show that such models are indeed incapable of handling unknown letters, which leads to catastrophic translation fai…
As a commercial provider of machine translation, we are constantly training engines for a variety of uses, languages, and content types. In each case, there can be many variables, such as the amount of training data available, and the quality requirements of the end user. These variables can have an impact on the robustness of Neural MT engines. On the whole, Neural MT cures many ills of other MT paradigms, but at the same time, it has introduced a new set of challenges to address. In this paper, we describe some of the specific issues with practical NMT and the approaches we take to improve m…
Evaluating the Efficacy of Length-Controllable Machine Translation
Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Artificial Intelligence Application Research Center, Huawei Technologies（华为技术有限公司人工智能应用研究中心）；School of Mathematical Sciences, Peking University（北京大学数学科学学院）
We consider two problems of NMT domain adaptation using meta-learning. First, we want to reach domain robustness, i.e., we want to reach high quality on both domains seen in the training data and unseen domains. Second, we want our systems to be adaptive, i.e., making it possible to finetune systems with just hundreds of in-domain parallel sentences. We study the domain adaptability of meta-learning when improving the domain robustness of the model. In this paper, we propose a novel approach, RMLNMT (Robust Meta-Learning Framework for Neural Machine Translation Domain Adaptation), which improv…
Baidu Research（百度研究院）；Oregon State University（俄勒冈州立大学）
This paper describes the machine translation system developed jointly by Baidu Research and Oregon State University for WMT 2019 Machine Translation Robustness Shared Task. Translation of social media is a very challenging problem, since its style is very different from normal parallel corpora (e.g. News) and also include various types of noises. To make it worse, the amount of social media parallel corpora is extremely limited. In this paper, we use a domain sensitive training method which leverages a large amount of parallel data from popular domains together with a little amount of parallel…
This paper outlines a theoretical framework using which different automatic metrics can be designed for evaluation of Machine Translation systems. It introduces the concept of {\em cognitive ease} which depends on {\em adequacy} and {\em lack of fluency}. Thus, cognitive ease becomes the main parameter to be measured rather than comprehensibility. The framework allows the components of cognitive ease to be broken up and computed based on different linguistic levels etc. Independence of dimensions and linearly combining them provides for a highly modular approach. The paper places the existing …
Several recent studies have reported dramatic performance improvements in neural machine translation (NMT) by augmenting translation at inference time with fuzzy-matches retrieved from a translation memory (TM). However, these studies all operate under the assumption that the TMs available at test time are highly relevant to the testset. We demonstrate that for existing retrieval augmented translation methods, using a TM with a domain mismatch to the test set can result in substantially worse performance compared to not using a TM at all. We propose a simple method to expose fuzzy-match NMT sy…
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）；Amazon（亚马逊）
Current Machine Translation (MT) models still struggle with more challenging input, such as noisy data and tail-end words and phrases. Several works have addressed this robustness issue by identifying specific categories of noise and variation then tuning models to perform better on them. An important yet under-studied category involves minor variations in nuance (non-typos) that preserve meaning w.r.t. the target language. We introduce and formalize this category as Natural Asemantic Variation (NAV) and investigate it in the context of MT robustness. We find that existing MT models fail when …
University of Wolverhampton（伍尔弗汉普顿大学）；University of Surrey（萨里大学）；De Montfort University（德蒙福特大学）
In translating text where sentiment is the main message, human translators give particular attention to sentiment-carrying words. The reason is that an incorrect translation of such words would miss the fundamental aspect of the source text, i.e. the author's sentiment. In the online world, MT systems are extensively used to translate User-Generated Content (UGC) such as reviews, tweets, and social media posts, where the main message is often the author's positive or negative attitude towards the topic of the text. It is important in such scenarios to accurately measure how far an MT system ca…
Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversarial source examples; (2) defend the translation model with adversarial target inputs to improve its robustness against the adversarial source inputs.For the generation of adversarial inputs, we propose a gradient-based method to craft adversarial examples informed by the translation loss over the clean inputs.Experimental results on Chinese-English a…
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）；Sogou Inc.（搜狗公司）；Tsinghua University（清华大学）；Huawei Noah’s Ark Lab, Huawei Technologies（华为技术有限公司华为诺亚方舟实验室）
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source. To solve this problem, we propose a simple but effective method to improve the robustness of NMT in the case of speech translation. We simulate the noise existing in the realistic output of the ASR system and inject them into the clean parallel data so that NMT can work under similar word distribution…
GAMBIT+: A Challenge Set for Evaluating Gender Bias in Machine Translation Quality Estimation Metrics
National Technical University of Athens（雅典国家技术大学）；Instituto de Telecomunicações（电信研究所）；University of Amsterdam（阿姆斯特丹大学）；Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；ELLIS Unit Lisbon（ELLIS里斯本单元）
Assessing and Improving Punctuation Robustness in English-Marathi Machine Translation
Computation for Indian Language Technology (CFILT) Department of Computer Science and Engineering（印度语言技术计算（CFILT）部门计算机科学与工程系）；Indian Institute of Technology Bombay（印度班加罗尔理工学院）
