• Home
  • Josef van Genabith
Josef van Genabith

Josef van Genabith
German Research Center for Artificial Intelligence DFKI · Multilingual Technologies MLT

PhD

About

325
Publications
47,229
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,839
Citations

Publications

Publications (325)
Preprint
Recent research on style transfer takes inspiration from unsupervised neural machine translation (UNMT), learning from large amounts of non-parallel data by exploiting cycle consistency loss, back-translation, and denoising autoencoders. By contrast, the use of self-supervised NMT (SSNMT), which leverages (near) parallel instances hidden in non-par...
Preprint
Full-text available
Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets. However, compared to original texts in the same language, translations possess distinct qualities referred to as translationese. Previous research has shown that these translati...
Article
Full-text available
This contribution describes the German EU Council Presidency Translator (EUC PT), a machine translation service created for the German EU Council Presidency in the second half of 2020, which is open to the general public. Following a series of earlier presidency translators, the German version exhibits important extensions and improvements. The Ger...
Preprint
Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been less explored for this task. In this work, we (i) compare the traditional feature-engineering-based approach t...
Preprint
For most language combinations, parallel data is either scarce or simply unavailable. To address this, unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic data generation techniques such as back-translation and noising, while self-supervised NMT (SSNMT) identifies parallel sentences in smaller compar...
Cover Page
Full-text available
Translatology is the theoretical and practical study of translation. It combines insights from linguistics, the humanities, cognitive and computer science to understand the process of translating between languages and the particular features characterizing language in translation. Central concepts of contemporary translatology are translationese, l...
Chapter
In this paper, we analyze a wide range of physiological, behavioral, performance, and subjective measures to estimate cognitive load (CL) during post-editing (PE) of machine translated (MT) text. To the best of our knowledge, the analyzed feature set comprises the most diverse set of features from a variety of modalities that has been investigated...
Conference Paper
Full-text available
This paper describes the UdS-DFKI submission to the shared task for unsupervised machine translation (MT) and very low-resource supervised MT between German (de) and Upper Sorbian (hsb) at the Fifth Conference of Machine Translation (WMT20). We submit systems for both the supervised and unsupervised tracks. Apart from various experimental approache...
Conference Paper
More and more professional translators are switching to the use of post-editing (PE) to increase productivity and reduce errors. Even though PE requires significantly less text production, current computer-aided translation (CAT) interfaces still heavily focus on traditional mouse and keyboard input and ignore other interaction modalities to suppor...
Preprint
Full-text available
Inflection is an essential part of every human language's morphology, yet little effort has been made to unify linguistic theory and computational methods in recent years. Methods of string manipulation are used to infer inflectional changes; our research question is whether a neural network would be capable of learning inflectional morphemes for i...
Preprint
Increasing the depth of models allows neural models to model complicated functions but may also lead to optimization issues. The Transformer translation model employs the residual connection to ensure its convergence. In this paper, we suggest that the residual connection has its drawbacks, and propose to train Transformers with the depth-wise LSTM...
Conference Paper
Current advances in machine translation (MT) increase the need for translators to switch from traditional translation to post-editing (PE) of machine-translated text, a process that saves time and reduces errors. This affects the design of translation interfaces, as the task changes from mainly generating text to correcting errors within otherwise...
Conference Paper
The shift from traditional translation to post-editing (PE) of machine-translated (MT) text can save time and reduce errors, but it also affects the design of translation interfaces, as the task changes from mainly generating text to correcting errors within otherwise helpful translation proposals. Since this paradigm shift offers potential for mod...
Conference Paper
Existing Neural Machine Translation (NMT) systems are generally trained on a large amount of sentence-level parallel data, and during prediction sentences are independently translated, ignoring cross-sentence contextual information. This leads to inconsistency between translated sentences. In order to address this issue, context-aware models have b...
Preprint
The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though intuitively the attentional network can connect distant words via shorter network paths than RNNs, empirical analy...
Preprint
The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the learning rate, comparatively few papers concentrate on the effect of batch size. In this paper, we analyze how inc...
Conference Paper
Full-text available
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cross-lingual and cross-cultural communication are still omnipresent. Language Technologies (LTs) are a powerful means to break down these barriers. While the last decade h...
Preprint
Self-supervised neural machine translation (SS-NMT) learns how to extract/select suitable training data from comparable -- rather than parallel -- corpora and how to translate, in a way that the two tasks support each other in a virtuous circle. SS-NMT has been shown to be competitive with state-of-the-art unsupervised NMT. In this study we provide...
Preprint
Full-text available
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cross-lingual and cross-cultural communication are still omnipresent. Language Technologies (LTs) are a powerful means to break down these barriers. While the last decade h...
Preprint
The Transformer translation model is popular for its effective parallelization and performance. Though a wide range of analysis about the Transformer has been conducted recently, the role of each Transformer layer in translation has not been studied to our knowledge. In this paper, we propose approaches to analyze the translation performed in encod...
Conference Paper
Translationese is a phenomenon present in human translations, simultaneous interpreting, and even machine translations. Some translationese features tend to appear in simultaneous interpreting with higher frequency than in human text translation, but the reasons for this are unclear. This study analyzes translationese patterns in translation, inter...
Preprint
The Transformer translation model employs residual connection and layer normalization to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. While several previous works show that even with residual connection and layer normalization, deep Transformers still have difficulty in training, and particularly a Transfo...
Preprint
We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information. We compare system performance on two different genres: news and TED talks. To do this, we manually annotate (the possibly incorrect) coreference chain...
Preprint
Full-text available
In this paper we present the UDS-DFKI system submitted to the Similar Language Translation shared task at WMT 2019. The first edition of this shared task featured data from three pairs of similar languages: Czech and Polish, Hindi and Nepali, and Portuguese and Spanish. Participants could choose to participate in any of these three tracks and submi...
Preprint
Full-text available
This paper describes strategies to improve an existing web-based computer-aided translation (CAT) tool entitled CATaLog Online. CATaLog Online provides a post-editing environment with simple yet helpful project management tools. It offers translation suggestions from translation memories (TM), machine translation (MT), and automatic post-editing (A...
Preprint
Full-text available
In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-source encoder based APE approaches. A research challenge now is the search for architectures that best support the capture, preparation and provision of src and mt inf...
Preprint
In this paper, we describe our submission to the English-German APE shared task at WMT 2019. We utilize and adapt an NMT architecture originally developed for exploiting context information to APE, implement this in our own transformer model and explore joint training of the APE task with a de-noising encoder.
Conference Paper
Full-text available
Phonemic Verbal Fluency (PVF) is a cogni-tive assessment task where a patient is asked to produce words constrained to a given alphabetical letter for a specified time duration. Patient production's are later evaluated based on strategies to reveal crucial diagnostic information by manually scoring results according to predetermined clinical criter...
Article
Full-text available
In this paper, we develop a model that uses a wide range of physiological and behavioral sensor data to estimate perceived cognitive load (CL) during post-editing (PE) of machine translated (MT) text. By predicting the subjectively reported perceived CL, we aim to quantify the extent of demands placed on the mental resources available during PE. Th...
Conference Paper
Current advances in machine translation increase the need for translators to switch from traditional translation to post-editing (PE) of machine-translated text, a process that saves time and improves quality. This affects the design of translation interfaces, as the task changes from mainly generating text to correcting errors within otherwise hel...
Preprint
Full-text available
Current advances in machine translation increase the need for translators to switch from traditional translation to post-editing of machine-translated text, a process that saves time and improves quality. Human and artificial intelligence need to be integrated in an efficient way to leverage the advantages of both for the translation task. This pap...
Article
This paper presents a comprehensive study on the use of translation memory software by translators of different backgrounds. We designed a questionnaire that was completed by a pool of 723 respondents including professional translators, translation students, and lecturers in translation studies and translation practice. We analyse the results of th...
Chapter
We describe a lexical resource-based process for query translation of a domain-specific and multilingual academic search engine in psychology, PubPsych. PubPsych queries are diverse in language with a high amount of informational queries and technical terminology. We present an approach for translating queries into English, German, French, and Span...
Conference Paper
This paper presents our English-German Automatic Post-Editing (APE) system submitted to the APE Task organized at WMT 2018 (Chatterjee et al., 2018). The proposed model is an extension of the transformer architecture: two separate self-attention-based encoders encode the machine translation output (mt) and the source (src), followed by a joint en-c...
Preprint
The advent of representation learning methods enabled large performance gains on various language tasks, alleviating the need for manual feature engineering. While engineered representations are usually based on some linguistic understanding and are therefore more interpretable, learned representations are harder to interpret. Empirically studying...
Conference Paper
Code-Mixing (CM) is the phenomenon of alternating between two or more languages which is prevalent in bi- and multi-lingual communities. Most NLP applications today are still designed with the assumption of a single interaction language and are most likely to break given a CM utterance with multiple languages mixed at a morphological, phrase or sen...
Article
Full-text available
The problem of a total absence of parallel data is present for a large number of language pairs and can severely detriment the quality of machine translation. We describe a language-independent method to enable machine translation between a low-resource language (LRL) and a third language, e.g. English. We deal with cases of LRLs for which there is...
Book
This book constitutes the refereed proceedings of the 18th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2018, held in Varna, Bulgaria, in September 2018. The 22 revised full papers and 7 poster papers presented were carefully reviewed and selected from 72 submissions. They cover a wide range of...
Article
End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with a large amount of parallel data available. Beside this palpable improvement, neural networks embrace several new properties. A single system can be trained to translate between many langua...
Article
Full-text available
In this paper, we investigate the application of text classification methods to support law professionals. We present several experiments applying machine learning techniques to predict with high accuracy the ruling of the French Supreme Court and the law area to which a case belongs to. We also investigate the influence of the time period in which...
Article
Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we p...
Article
Full-text available
In this paper, we investigate the application of text classification methods to predict the law area and the decision of cases judged by the French Supreme Court. We also investigate the influence of the time period in which a ruling was made over the textual form of the case description and the extent to which it is necessary to mask the judge's m...
Article
Full-text available
This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small changes in the input such as non-canonical input (e.g., typos). Yet both stability and robustness are desired properties in applications invo...
Conference Paper
Full-text available
In this paper we combine two strands of machine translation (MT) research: automatic post-editing (APE) and multi-engine (system combination) MT. APE systems learn a target-language-side second stage MT system from the data produced by human corrected output of a first stage MT system, to improve the output of the first stage MT in what is essentia...