Generalization to unseen instances is our eternal pursuit for all data-driven models. However, for realistic task like machine translation, the traditional approach measuring generalization in an average sense provides poor understanding for the fine-grained generalization ability. As a remedy, this paper attempts to identify and understand generalization barrier words within an unseen input sentence that \textit{cause} the degradation of fine-grained generalization. We propose a principled definition of generalization barrier words and a modified version which is tractable in computation. Based on the modified one, we propose three simple methods for barrier detection by the search-aware risk estimation through counterfactual generation. We then conduct extensive analyses on those detected generalization barrier words on both Zh$\Leftrightarrow$En NIST benchmarks from various perspectives. Potential usage of the detected barrier words is also discussed.
University of Zurich（苏黎世大学）；University of Edinburgh（爱丁堡大学）
Omission and addition of content is a typical issue in neural machine translation. We propose a method for detecting such phenomena with off-the-shelf translation models. Using contrastive conditioning, we compare the likelihood of a full sequence under a translation model to the likelihood of its parts, given the corresponding source or target sequence. This allows to pinpoint superfluous words in the translation and untranslated words in the source even in the absence of a reference translation. The accuracy of our method is comparable to a supervised method that requires a custom quality es…
Rule-based machine translation is more data efficient than the big data-based machine translation approaches, making it appropriate for languages with low bilingual corpus resources -- i.e., minority languages. However, the rule-based approach has declined in popularity relative to its big data cousins primarily because of the extensive training and labour required to define the language rules. To address this, we present a semantic representation that 1) treats all bits of meaning as individual concepts that 2) modify or further specify one another to build a network that relates entities in …
Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. In this work, we first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinated vs. non-hallucinated outputs generated via source perturbations. We then show that these symptoms are reliable indicators of natural hallucinations, by using them to design a ligh…
While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate, previously existing methods fall short and even the standard sequence log-probability is more informative. It means that characteristics internal to the model can give much more information than we expect, and before using external models and measures, we first need to ask: how far can we go if we use nothing but the translation model itself ? We propose to u…
We detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure of uncertainty designed specifically for long sequences of discrete random variables -- i.e. words in the output sentence. Our new measure of uncertainty solves a major intractability in the naive application of existing approaches on long sentences. We use our new measure on a Transformer model trained with dropout approximate inference. On the task of German-English translation using WMT13 and Europarl, we show tha…
Spoken Language Translation (SLT) is becoming more widely used and becoming a communication tool that helps in crossing language barriers. One of the challenges of SLT is the translation from a language without gender agreement to a language with gender agreement such as English to Arabic. In this paper, we introduce an approach to tackle such limitation by enabling a Neural Machine Translation system to produce gender-aware translation. We show that NMT system can model the speaker/listener gender information to produce gender-aware translation. We propose a method to generate data used in ad…
Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation
CentraleSupélec（中央高等电力学院）；Universite Paris-Saclay（巴黎萨克雷大学）；Inria（法国国家信息与自动化研究所）；CEA（法国原子能和替代能源委员会）；digeiz；Equall；Instituto de Telecomunicações（电信研究所）；University of Lisbon（里斯本大学）；Unbabel
Machine translation has made rapid advances in recent years. Millions of people are using it today in online translation systems and mobile applications in order to communicate across language barriers. The question naturally arises whether such systems can approach or achieve parity with human translations. In this paper, we first address the problem of how to define and accurately measure human parity in translation. We then describe Microsoft's machine translation system and measure the quality of its translations on the widely used WMT 2017 news translation task from Chinese to English. We…
University of Toronto（多伦多大学）；Vector Institute（矢量研究所）；Academia Sinica（中央研究院）；Toronto Rehabilitation Institute（多伦多康复研究所）
Machine learning has shown promise for automatic detection of Alzheimer's disease (AD) through speech; however, efforts are hampered by a scarcity of data, especially in languages other than English. We propose a method to learn a correspondence between independently engineered lexicosyntactic features in two languages, using a large parallel corpus of out-of-domain movie dialogue data. We apply it to dementia detection in Mandarin Chinese, and demonstrate that our method outperforms both unilingual and machine translation-based baselines. This appears to be the first study that transfers feat…
University of Wuppertal（伍珀塔尔大学）；University of Konstanz（康斯坦茨大学）；FIZ Karlsruhe（卡尔斯鲁厄专业信息中心）
Identifying cross-language plagiarism is challenging, especially for distant language pairs and sense-for-sense translations. We introduce the new multilingual retrieval model Cross-Language Ontology-Based Similarity Analysis (CL-OSA) for this task. CL-OSA represents documents as entity vectors obtained from the open knowledge graph Wikidata. Opposed to other methods, CL-OSA does not require computationally expensive machine translation, nor pre-training using comparable or parallel corpora. It reliably disambiguates homonyms and scales to allow its application to Web-scale document collection…
ADAPT Centre（ADAPT中心）；School of Computing, Dublin（都柏林计算机学院）
Every day, more people are becoming infected and dying from exposure to COVID-19. Some countries in Europe like Spain, France, the UK and Italy have suffered particularly badly from the virus. Others such as Germany appear to have coped extremely well. Both health professionals and the general public are keen to receive up-to-date information on the effects of the virus, as well as treatments that have proven to be effective. In cases where language is a barrier to access of pertinent information, machine translation (MT) may help people assimilate information published in different languages.…
Due to the nature of human language, historical documents are hard to comprehend by contemporary people. This limits their accessibility to scholars specialized in the time period in which the documents were written. Modernization aims at breaking this language barrier by generating a new version of a historical document, written in the modern version of the document's original language. However, while it is able to increase the document's comprehension, modernization is still far from producing an error-free version. In this work, we propose a collaborative framework in which a scholar can wo…
Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology（日本国立情报学研究所）
Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network. The capacity of the memory network that detecting the most relevant part of the current sentence from memory renders a natural solution to model the rich document-level context. In this work, the proposed document-aware memory network is implemented to enhance the Tran…
Interactions, LLC；Murray Hill, NJ, USA（美国新泽西州默里希尔（注：此处为地址，非机构，按要求不应提取。正确机构仅为Interactions, LLC））
With the resurgence of chat-based dialog systems in consumer and enterprise applications, there has been much success in developing data-driven and rule-based natural language models to understand human intent. Since these models require large amounts of data and in-domain knowledge, expanding an equivalent service into new markets is disrupted by language barriers that inhibit dialog automation. This paper presents a user study to evaluate the utility of out-of-the-box machine translation technology to (1) rapidly bootstrap multilingual spoken dialog systems and (2) enable existing human anal…
Multiword expressions (MWEs) present groups of words in which the meaning of the whole is not derived from the meaning of its parts. The task of processing MWEs is crucial in many natural language processing (NLP) applications, including machine translation and terminology extraction. Therefore, detecting MWEs is a popular research theme. In this paper, we explore state-of-the-art neural transformers in the task of detecting MWEs.We empirically evaluate several transformer models in the dataset for SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM). We show that…
High-performing machine translation (MT) systems can help overcome language barriers while making it possible for everyone to communicate and use language technologies in the language of their choice. However, such systems require large amounts of parallel sentences for training, and translators can be difficult to find and expensive. Here, we present a data collection strategy for MT which, in contrast, is cheap and simple, as it does not require bilingual speakers. Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to c…
Cross-lingual plagiarism (CLP) occurs when texts written in one language are translated into a different language and used without acknowledging the original sources. One of the most common methods for detecting CLP requires online machine translators (such as Google or Microsoft translate) which are not always available, and given that plagiarism detection typically involves large document comparison, the amount of translations required would overwhelm an online machine translator, especially when detecting plagiarism over the web. In addition, when translated texts are replaced with their sy…
All over the world and especially in Africa, researchers are putting efforts into building Neural Machine Translation (NMT) systems to help tackle the language barriers in Africa, a continent of over 2000 different languages. However, the low-resourceness, diacritical, and tonal complexities of African languages are major issues being faced. The FFR project is a major step towards creating a robust translation model from Fon, a very low-resource and tonal language, to French, for research and public use. In this paper, we introduce FFR Dataset, a corpus of Fon-to-French translations, describe …
Meta AI；UC Berkeley（加州大学伯克利分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today. However, such efforts have coalesced around a small subset of languages, leaving behind the vast majority of mostly low-resource languages. What does it take to break the 200 language barrier while ensuring safe, high quality results, all while keeping ethical considerations in mind? In No Language Left Behind, we took on this challenge by first contextualizing the need for low-resource language translation support through ex…
The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure
Johns Hopkins University, Center for Language and Speech Processing（约翰霍普金斯大学，语言与语音处理中心）；Language Technologies Institute, Carnegie Mellon University（语言技术研究所，卡内基梅隆大学）
Towards cross-cultural study of folksong lyrics with machine translation
Charles University（查理大学）；University of Music and Performing Arts Graz（格拉茨音乐与表演艺术大学）；Graduate School of Culture Technology（文化技术研究生院）；KAIST（韩国科学技术院）；Utrecht University（乌得勒支大学）；Institute of Ethnology（民族学研究所）；Czech Academy of Sciences（捷克科学院）；Estonian Literary Museum（爱沙尼亚文学博物馆）；NAS of Ukraine（乌克兰国家科学院）
We present MeetDot, a videoconferencing system with live translation captions overlaid on screen. The system aims to facilitate conversation between people who speak different languages, thereby reducing communication barriers between multilingual participants. Currently, our system supports speech and captions in 4 languages and combines automatic speech recognition (ASR) and machine translation (MT) in a cascade. We use the re-translation strategy to translate the streamed speech, resulting in caption flicker. Additionally, our system has very strict latency requirements to have acceptable c…
Over 800 languages are spoken across West Africa. Despite the obvious diversity among people who speak these languages, one language significantly unifies them all - West African Pidgin English. There are at least 80 million speakers of West African Pidgin English. However, there is no known natural language processing (NLP) work on this language. In this work, we perform the first NLP work on the most popular variant of the language, providing three major contributions. First, the provision of a Pidgin corpus of over 56000 sentences, which is the largest we know of. Secondly, the training of …
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）
Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found in training data, specifically superficial word co-occurrences, rather than a deeper understanding of the source text. We introduce a method for the prediction of disambiguation errors based on statistical data properties, demonstrating its effectiveness across several domains and model types. Moreover, we develop a simple adversarial attack strategy that minimally perturbs sentences in order to eli…
We present a novel approach to detecting over and under translations (OT/UT) as part of adequacy error checks in translation evaluation. We do not restrict ourselves to machine translation (MT) outputs and specifically target applications with human generated translation pipeline. The goal of our system is to identify OT/UT errors from human translated video subtitles with high error recall. We achieve this without reference translations by learning a model on synthesized training data. We compare various classification networks that we trained on embeddings from pre-trained language model wit…
BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation
School of Computer Engineering and Science, Shanghai University, Shanghai, China（1 上海大学计算机工程与科学学院，上海，中国）；Funstory.ai Limited, Hong Kong SAR, China（2 Funstory.ai有限公司，香港特别行政区，中国）；Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China（3 上海交通大学计算机科学与工程系，上海，中国）
Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present \textbf{AVMuST-TED}, the first dataset for \textbf{A}udio-\textbf{V}isual \textbf{Mu}ltilingual \textbf{S}peech \textbf{T}ranslation, derived from \textbf{…
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Department of Computer Science and Engineering, University of Texas at Arlington（德克萨斯大学阿灵顿分校计算机科学与工程系）
Entity alignment is the task of finding entities in two knowledge bases (KBs) that represent the same real-world object. When facing KBs in different natural languages, conventional cross-lingual entity alignment methods rely on machine translation to eliminate the language barriers. These approaches often suffer from the uneven quality of translations between languages. While recent embedding-based techniques encode entities and relationships in KBs and do not need machine translation for cross-lingual entity alignment, a significant number of attributes remain largely unexplored. In this pap…
NetEase Youdao Information Technology (Beijing) Co., LTD.（网易有道信息技术（北京）有限公司）
In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using …
XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
Google DeepMind（谷歌DeepMind）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；International Centre for Theoretical Sciences, Tata Institute of Fundamental Research（理论科学国际中心， Tata 基础研究机构）
Bangladesh Atomic Energy Commission（孟加拉国原子能委员会）；University of Calgary（卡尔加里大学）；American International University-Bangladesh（孟加拉国美国国际大学）；City University（城市大学）；Concordia University（康考迪亚大学）
Making computer programming language more understandable and easy for the human is a longstanding problem. From assembly language to present day's object-oriented programming, concepts came to make programming easier so that a programmer can focus on the logic and the architecture rather than the code and language itself. To go a step further in this journey of removing human-computer language barrier, this paper proposes machine learning approach using Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM) to convert human language into programming language code. The programmer will…
KDDI Research, Inc.（KDDI综合研究所）；The University of Tokyo（东京大学）
Machine-translated text plays a crucial role in the communication of people using different languages. However, adversaries can use such text for malicious purposes such as plagiarism and fake review. The existing methods detected a machine-translated text only using the text's intrinsic content, but they are unsuitable for classifying the machine-translated and human-written texts with the same meanings. We have proposed a method to extract features used to distinguish machine/human text based on the similarity between the intrinsic text and its back-translation. The evaluation of detecting t…
We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we …
Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation
Robert Koch Institute（罗伯特·科赫研究所）；European Commission（欧洲委员会）；Deree-The American College of Greece（希腊 Deree 美国学院）；Åbo Akademi University（奥布学术大学）；Arcada University of Applied Sciences（阿卡达应用科学大学）；University of Münster（明斯特大学）
