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 computation for this metric is intractable, we employ an efficient approach as its approximation. On six standard translation tasks, we quantitatively evaluate several explanation methods in terms of the proposed metric and we reveal some valuable findings for these explanation methods in our experiments.
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-…
In this paper we present an application of explanation-based learning (EBL) in the parsing module of a real-time English-Spanish machine translation system designed to translate closed captions. We discuss the efficiency/coverage trade-offs available in EBL and introduce the techniques we use to increase coverage while maintaining a high level of space and time efficiency. Our performance results indicate that this approach is effective.
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…
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 tren…
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 …
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…
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…
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…
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…
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）
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 …
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…
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）
Georgia Institute of Technology（佐治亚理工学院）；University of Kentucky（肯塔基大学）
We introduce AI rationalization, an approach for generating explanations of autonomous system behavior as if a human had performed the behavior. We describe a rationalization technique that uses neural machine translation to translate internal state-action representations of an autonomous agent into natural language. We evaluate our technique in the Frogger game environment, training an autonomous game playing agent to rationalize its action choices using natural language. A natural language training corpus is collected from human players thinking out loud as they play the game. We motivate th…
Nanyang Technological University（南洋理工大学）；Salesforce Research Asia（赛富时亚洲研究院）；Sofia University（索非亚大学）；Qatar Computing Research Institute（卡塔尔计算研究所）
The ongoing neural revolution in machine translation has made it easier to model larger contexts beyond the sentence-level, which can potentially help resolve some discourse-level ambiguities such as pronominal anaphora, thus enabling better translations. Unfortunately, even when the resulting improvements are seen as substantial by humans, they remain virtually unnoticed by traditional automatic evaluation measures like BLEU, as only a few words end up being affected. Thus, specialized evaluation measures are needed. With this aim in mind, we contribute an extensive, targeted dataset that can…
The Hebrew University of Jerusalem（希伯来大学）；Bar Ilan University（巴伊兰大学）
Machine translation (MT) requires a wide range of linguistic capabilities, which current end-to-end models are expected to learn implicitly by observing aligned sentences in bilingual corpora. In this work, we ask: \emph{How well do MT models learn coreference resolution from implicit signal?} To answer this question, we develop an evaluation methodology that derives coreference clusters from MT output and evaluates them without requiring annotations in the target language. We further evaluate several prominent open-source and commercial MT systems, translating from English to six target langu…
Manipal Institute of Technology（马尼帕尔理工学院）；MAHE（马尼帕尔高等教育学院）
With language models being deployed increasingly in the real world, it is essential to address the issue of the fairness of their outputs. The word embedding representations of these language models often implicitly draw unwanted associations that form a social bias within the model. The nature of gendered languages like Hindi, poses an additional problem to the quantification and mitigation of bias, owing to the change in the form of the words in the sentence, based on the gender of the subject. Additionally, there is sparse work done in the realm of measuring and debiasing systems for Indic …
Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations
Boston University（波士顿大学）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；UPenn（宾夕法尼亚大学）；MIT（麻省理工学院）；Monash University Indonesia（蒙纳士大学印度尼西亚校区）
The rapid development of large pretrained language models has revolutionized not only the field of Natural Language Generation (NLG) but also its evaluation. Inspired by the recent work of BARTScore: a metric leveraging the BART language model to evaluate the quality of generated text from various aspects, we introduce DATScore. DATScore uses data augmentation techniques to improve the evaluation of machine translation. Our main finding is that introducing data augmented translations of the source and reference texts is greatly helpful in evaluating the quality of the generated translation. We…
The scientific community is increasingly aware of the necessity to embrace pluralism and consistently represent major and minor social groups. Currently, there are no standard evaluation techniques for different types of biases. Accordingly, there is an urgent need to provide evaluation sets and protocols to measure existing biases in our automatic systems. Evaluating the biases should be an essential step towards mitigating them in the systems. This paper introduces WinoST, a new freely available challenge set for evaluating gender bias in speech translation. WinoST is the speech version of W…
Center for Information and Language Processing（信息与语言处理中心）；LMU Munich（慕尼黑大学）
The behavior of deep neural networks (DNNs) is hard to understand. This makes it necessary to explore post hoc explanation methods. We conduct the first comprehensive evaluation of explanation methods for NLP. To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems. Both paradigms require no manual annotation and are therefore broadly applicable. We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP. We show empirically that LIMSSE, LRP and DeepLIFT are the most effectiv…
