Translationese Indicators for Human Translation Quality Estimation (based on English-to-Russian Translation of Mass-media Texts). PDF Download

Author: Maria Kunilovskaya
Publisher:
ISBN:
Category :
Languages : en
Pages : 0

View

Book Description

Author: Lucia Specia
Publisher: Springer Nature
ISBN: 3031021681
Category : Computers
Languages : en
Pages : 148

View

Book Description
Many applications within natural language processing involve performing text-to-text transformations, i.e., given a text in natural language as input, systems are required to produce a version of this text (e.g., a translation), also in natural language, as output. Automatically evaluating the output of such systems is an important component in developing text-to-text applications. Two approaches have been proposed for this problem: (i) to compare the system outputs against one or more reference outputs using string matching-based evaluation metrics and (ii) to build models based on human feedback to predict the quality of system outputs without reference texts. Despite their popularity, reference-based evaluation metrics are faced with the challenge that multiple good (and bad) quality outputs can be produced by text-to-text approaches for the same input. This variation is very hard to capture, even with multiple reference texts. In addition, reference-based metrics cannot be used in production (e.g., online machine translation systems), when systems are expected to produce outputs for any unseen input. In this book, we focus on the second set of metrics, so-called Quality Estimation (QE) metrics, where the goal is to provide an estimate on how good or reliable the texts produced by an application are without access to gold-standard outputs. QE enables different types of evaluation that can target different types of users and applications. Machine learning techniques are used to build QE models with various types of quality labels and explicit features or learnt representations, which can then predict the quality of unseen system outputs. This book describes the topic of QE for text-to-text applications, covering quality labels, features, algorithms, evaluation, uses, and state-of-the-art approaches. It focuses on machine translation as application, since this represents most of the QE work done to date. It also briefly describes QE for several other applications, including text simplification, text summarization, grammatical error correction, and natural language generation.

Author: Maria Kunilovskaya
Publisher:
ISBN:
Category :
Languages : en
Pages : 0

View

Book Description
This note is part of Quality testing.

Author: Joss Moorkens
Publisher: Springer
ISBN: 3319912410
Category : Computers
Languages : en
Pages : 292

View

Book Description
This is the first volume that brings together research and practice from academic and industry settings and a combination of human and machine translation evaluation. Its comprehensive collection of papers by leading experts in human and machine translation quality and evaluation who situate current developments and chart future trends fills a clear gap in the literature. This is critical to the successful integration of translation technologies in the industry today, where the lines between human and machine are becoming increasingly blurred by technology: this affects the whole translation landscape, from students and trainers to project managers and professionals, including in-house and freelance translators, as well as, of course, translation scholars and researchers. The editors have broad experience in translation quality evaluation research, including investigations into professional practice with qualitative and quantitative studies, and the contributors are leading experts in their respective fields, providing a unique set of complementary perspectives on human and machine translation quality and evaluation, combining theoretical and applied approaches.

Author: Malcolm Williams
Publisher: University of Ottawa Press
ISBN: 0776617362
Category : Language Arts & Disciplines
Languages : en
Pages : 209

View

Book Description
Outlining an original, discourse-based model for translation quality assessment that goes beyond conventional microtextual error analysis, Malcolm Williams explores the potential of transferring reasoning and argument as the prime criterion of translation quality. Assessment through error analysis is inevitably based on an error count - an unsatisfactory means of establishing, and justifying, differences in quality that forces the evaluator to focus on subsentence elements rather than the key messages of the source text. Williams counters that a judgment of translation quality should be based primarily on the success with which the translator has rendered the reasoning, or argument structure. Six aspects for assessment are proposed: argument macrostructure, propositional functions, conjunctives, types of arguments, figures of speech, and narrative strategy. Williams illustrates the approach using three different types of examples: letters, statistical reports, and argumentative articles for publication. Translation Quality Assessment offers translators a new set of flexible and modular standards.

Author: Juliane House
Publisher: Routledge
ISBN: 1317619315
Category : Language Arts & Disciplines
Languages : en
Pages : 185

View

Book Description
Translation Quality Assessment has become one of the key issues in translation studies. This comprehensive and up-to-date treatment of translation evaluation makes explicit the grounds of judging the worth of a translation and emphasizes that translation is, at its core, a linguistic art. Written by the author of the world’s best known model of translation quality assessment, Juliane House provides an overview of relevant contemporary interdisciplinary research on intercultural communication and globalization research, corpus and psycho- and neurolinguistic studies. House also acknowledges the importance of socio-cultural and situational context in which texts are embedded, and which need to be analysed when they are transferred through space and time in acts of translation but also highlights the linguistic art form of translation. The text includes a newly revised and presented model of translation quality assessment which, like its predecessor, relies on detailed textual and culturally informed contextual analysis and comparison. The test cases also show that there are two steps in translation evaluation: firstly analysis, description and explanation; secondly, judgements of value, socio-cultural relevance and appropriateness. The second is futile without the first: to judge is easy, to understand less so. Translation Quality Assessment is an invaluable resource for students and researchers of Translation Studies and Intercultural Communication, as well as for professional translators.

Author: Carol Maier
Publisher: Routledge
ISBN: 1317640845
Category : Language Arts & Disciplines
Languages : en
Pages : 237

View

Book Description
The definition of value or quality with respect to work in translation has historically been a particularly vexed issue. Today, however, the growing demand for translations in such fields as technology and business and the increased scrutiny of translators' work by scholars in many disciplines is giving rise to a need for more nuanced, more specialized, and more explicit methods of determining value. Some refer to this determination as evaluation, others use the term assessment. Either way, the question is one of measurement and judgement, which are always unavoidably subjective and frequently rest on criteria that are not overtly expressed. This means that devising more complex evaluative practices involves not only quantitative techniques but also an exploration of the attitudes, preferences, or individual values on which criteria are established. Intended as an interrogation and a critique that can serve to prompt a more thorough and open consideration of evaluative criteria, this special issue of The Translator offers examinations of diverse evaluative practices and contains both empirical and hermeneutic work. Topics addressed include the evaluation of student translations using more up-to-date and positive methods such as those employed in corpus studies; the translation of non?standard language; translation into the second language; terminology; the application of theoretical criteria to practice; a social?textual perspective; and the reviewing of literary translations in the press. In addition, reviews by a number of literary translators discuss specific translations both into and out of English.

Author: Juliane House
Publisher:
ISBN:
Category : Language Arts & Disciplines
Languages : en
Pages : 368

View

Book Description

Author: Tatyana Bystrova-McIntyre
Publisher:
ISBN:
Category : Russian language
Languages : en
Pages : 405

View

Book Description
The textual turn in translation studies in the 1980s shifted the focus of translation research from smaller, sub-sentential textual units, such as words and phrases, to global features that run throughout entire texts, such as cohesion, coherence, and other features of textual organization (Neubert & Shreve 1992). Nevertheless, in the current practice of translation, where content is translated by teams of translators using a variety of technologies, such as translation memories and machine translation, the focus often shifts back to sub-sentential segments, threatening the maintenance of a global textual orientation. These realities of the industry make the need for empirical studies of cohesive and other global textual features of vital importance. Additionally, given the explosive growth of machine translation in recent years, it seems relevant to supplement the studies of global features in human-translated texts by similar studies of machine-translated output. This empirical corpus-based study compares the use of cohesive devices and other global textual features across three corpora organized by genre (literary, newspaper, and scientific). Each of these corpora was divided into three sub-corpora based on the method of text production: texts written in English (non-translated texts), texts translated into English from Russian by human translators (human-translated texts), and texts translated into English from Russian by a machine translation tool (machine-translated texts). This study applies a more comprehensive approach than has been used earlier for analyzing global features of texts produced by different methods in corpora of different text-types. It employs the framework for studying cohesive and other global features of texts suggested by Dong and Lan (2010), who combined Halliday & Hasan's pioneering ideas for studying cohesion in English (1976) with Campbell's construct of textual competence (1998). In addition to reference and conjunction cohesive devices, this study looks at nominalization, lexical density, average word length, average sentence length, passives, and prepositional phrases. The study sheds light on global characteristics of translated texts--whether and to what extent human and machine translations differ from non-translated texts--contributing to existing studies of translation universals and laws of translation. Furthermore, by including machine-translated texts as a third dimension of research, in addition to the more typically studied non-translated and human-translated texts, this study addresses questions of whether translation universals and laws of interference are at work in machine-translated texts to the same extent as in human-translated texts. The study also includes a comparison of genre-specific characteristics of literary, newspaper, and scientific texts across non-translated, human-translated, and machine-translated corpora. The results of this study are then used to design practical recommendations for translators, editors of human and machine translations, translation evaluators, and translator trainers.

Author: Ilse Depraetere
Publisher: Walter de Gruyter
ISBN: 3110259885
Category : Language Arts & Disciplines
Languages : en
Pages : 285

View

Book Description
The volume is a collection of papers that deal with the issue of translation quality from a number of perspectives. It addresses the quality of human translation and machine translation, of pragmatic and literary translation, of translations done by students and by professional translators. Quality is not merely looked at from a linguistic point of view, but the wider context of QA in the translation workflow also gets ample attention. The authors take an inductive approach: the papers are based on the analysis of translation data and/or on hands-on experience. The book provides a bird's eye view of the crucial quality issues, the close collaboration between academics and industry professionals safeguarding attention for quality in the 'real world'. For this reason, the methodological stance is likely to inspire the applied researcher. The analyses and descriptions also include best practices for translation trainers, professional translators and project managers.