Human Translation Process Research Articles

Innovative methods for integrating translation memory and CAT tools: Enhancing intelligent support in human translation processes

This paper explores the innovative integration of Translation Memory (TM) and Computer-Assisted Translation (CAT) tools to enhance translation efficiency, consistency, and quality in multinational organizations. By adopting a user-centric interface design, modular system architecture, and cloud-based deployment, the integrated system addresses diverse translation needs while ensuring data security and privacy. Key features include real-time translation suggestions powered by machine learning algorithms, seamless access to TM databases, and real-time collaboration tools. The paper discusses implementation strategies, challenges, and solutions, highlighting the importance of user training and continuous improvement. A case study demonstrates significant improvements in translation speed, accuracy, and user satisfaction, underscoring the potential of advanced translation technologies to transform translation workflows. The findings provide valuable insights into best practices for successful implementation and optimization of TM and CAT tools in complex, large-scale environments.

An Active Inference Agent for Modeling Human Translation Processes.

This paper develops an outline for a hierarchically embedded architecture of an artificial agent that models human translation processes based on principles of active inference (AIF) and predictive processing (PP). AIF and PP posit that the mind constructs a model of the environment which guides behavior by continually generating and integrating predictions and sensory input. The proposed model of the translation agent consists of three processing strata: a sensorimotor layer, a cognitive layer, and a phenomenal layer. Each layer consists of a network of states and transitions that interact on different time scales. Following the AIF framework, states are conditioned on observations which may originate from the environment and/or the embedded processing layer, while transitions between states are conditioned on actions that implement plans to optimize goal-oriented behavior. The AIF agent aims at simulating the variation in translational behavior under various conditions and to facilitate investigating the underlying mental mechanisms. It provides a novel framework for generating and testing new hypotheses of the translating mind.

Exploring Human-Like Translation Strategy with Large Language Models

Abstract Large language models (LLMs) have demonstrated impressive capabilities in general scenarios, exhibiting a level of aptitude that approaches, in some aspects even surpasses, human-level intelligence. Among their numerous skills, the translation abilities of LLMs have received considerable attention. Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process, which might take preparatory steps to ensure high-quality translation. This work explores this possibility by proposing the MAPS framework, which stands for Multi-Aspect Prompting and Selection. Specifically, we enable LLMs first to analyze the given source sentence and induce three aspects of translation-related knowledge (keywords, topics, and relevant demonstrations) to guide the final translation process. Moreover, we employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge. Both automatic (3 LLMs × 11 directions × 2 automatic metrics) and human evaluation (preference study and MQM) demonstrate the effectiveness of MAPS. Further analysis shows that by mimicking the human translation process, MAPS reduces various translation errors such as hallucination, ambiguity, mistranslation, awkward style, untranslated text, and omission. Source code is available at https://github.com/zwhe99/MAPS-mt.

Empirical translation process research

Abstract Over the last four decades, considerable efforts have been devoted to the modeling and evaluation of human translation processes. This article takes a closer look at the evolution of empirical Translation Process Research (TPR) within the CRITT TPR-DB tradition. It contends that human translation unfolds on various processing levels and puts forth the Free Energy Principle (FEP) and Active Inference (AIF) as a promising framework for modeling these intricately embedded processes in a mathematically rigorous framework. The article introduces innovative methods for quantifying fundamental concepts of Relevance Theory (relevance, s-mode, and i-mode translation) and establishes their connection with the Monitor Model, framing relevance maximization as a special case of free energy minimization. The framework presents exciting prospects for future research in predictive TPR, promising to enhance our understanding of human translation processes and contributing significantly to the broader field of translation studies and cognitive sciences in general.

Audiovisual translation, translators, and technology: From automation pipe dream to human–machine convergence

Audiovisual translation (AVT), broadly understood as a synonym for media content localization, and not only as a particular practice of linguistic transfer, is undergoing a revolution that was unthinkable only a few years ago – even in those territories where viewers are less accustomed to localized content. Digitalization and technological changes, which have had such an impact on the way audiovisual texts – whether original, localized, or adapted – are produced, distributed, edited, consumed, and shared have also had a substantial impact on the AVT profession. This article explores the ways in which technology has been evolving as an aid to translators: from being merely a clerical aid for transcribing digital texts to automating tasks and integrating machine translation into human translation processes. This it does by providing a range of tools to assist translators in their work processes, progressively migrating both tools and processes to cloud-based environments. The focus is then on AVT, and more particularly on dubbing, where digitalization has shaped the consumer market and posed several challenges to language technology developments and AVT professional practices. Academia has also paid attention to such developments and has increasingly dealt with a number of matters affecting both practice and training to cater to the needs of current media markets. A final word is devoted to proposing a literacy-based framework for the training of translators that embraces technology so as to incorporate automation as an additional aid and which redefines the audiovisual translator’s workstation.

Cognitive effort in human translation and machine translation post-editing processes

Abstract Due to the inaccuracies of Machine Translation (MT), Post-Editing (PE) is inevitable. This poses questions over whether human effort to polish an MT is worthwhile or whether it would be more efficient to translate manually. However, to date, fewer attempts have been made to compare the cognitive effort in the PE process and the sub-phases (orientation, drafting, and revision) of PE with that of Human Translation (HT). To fill this gap, the current study aims to investigate and compare cognitive effort in HT and PE processes in translation from Chinese to English. Data were collected via eye-tracking and keyboard-logging approaches from 25 participants recruited to fulfil three HT and three PE tasks respectively. The comparison of cognitive effort was made from the processes of HT and PE, and their different sub-phases. The study reveals a significant difference in cognitive effort, orientation duration, and drafting duration between HT and PE.

Effect of text type on translation effort in human translation and neural machine translation post-editing processes: evidence from eye-tracking and keyboard-logging

ABSTRACT Text type influences the translator’s decision in taking an overall translation approach and consequently selecting translation techniques. While the majority of studies to date have investigated this phenomenon as an end-product, the effect of text types on the translation process has received little attention in the area of cognitive translation processes, especially from an empirical perspective. To fill this gap, the current study employed eye-tracking and keyboard-logging approaches to investigate the effect of text type (informative text, expressive text, and operative text) on the cognitive efforts demanded in the Human Translation (HT) and Neural Machine Translation Post-Editing (PE) processes. The data was collected from 24 participants (12 professional translators and 12 undergraduate students), who were required to manually translate and post-edit three text types from Chinese into English. From the findings, it appears that text types affect the translator’s time investment, mental process, and technical input in both HT and PE processes. The findings also suggest that PE, as one mode of Human–Computer Interaction, emancipates translators from the effortful task of traditional from-scratch translation, and this effort change is also affected by the text type. The study has practical implications for both translators and translator training.

Models of the Translation Process and the Free Energy Principle.

Translation process research (TPR) has generated a large number of models that aim at explaining human translation processes. In this paper, I suggest an extension of the monitor model to incorporate aspects of relevance theory (RT) and to adopt the free energy principle (FEP) as a generative model to elucidate translational behaviour. The FEP-and its corollary, active inference-provide a general, mathematical framework to explain how organisms resist entropic erosion so as to remain within their phenotypic bounds. It posits that organisms reduce the gap between their expectations and observations by minimising a quantity called free energy. I map these concepts on the translation process and exemplify them with behavioural data. The analysis is based on the notion of translation units (TUs) which exhibit observable traces of the translator's epistemic and pragmatic engagement with their translation environment, (i.e., the text) that can be measured in terms of translation effort and effects. Sequences of TUs cluster into translation states (steady state, orientation, and hesitation). Drawing on active inference, sequences of translation states combine into translation policies that reduce expected free energy. I show how the notion of free energy is compatible with the concept of relevance, as developed in RT, and how essential concepts of the monitor model and RT can be formalised as deep temporal generative models that can be interpreted under a representationalist view, but also support a non-representationalist account.

La constitución de una memoria terminológica: elaboración de terminologías bilingües en programas de memoria de traducción

Computer-aided translation systems (CAT) based on Translation Memories (TM) are a widely diffused technology that uses database and code-protection features to improve the quality, efficiency and consistency of the human translation process. These systems basically consist of a textual database in which each source sentence of a translation is stored together with the target sentence (this is called a translation memory “unit”). New and changed translation proposals will then be stored in the database for future use. This textual database – the kernel of the system – is combined with a terminological database (TDB), which is used by translators to store independently, terminological equivalences or translation units of particular value.In this paper the authors outline a first draft of a methodology that describes the preparation of a bilingual terminology from – and within – TM applications. The bilingual corpus produced is called the ‘terminological memory’ of the translator.

A survey of machine translation competences: Insights for translation technology educators and practitioners

This paper describes a large-scale survey of machine translation (MT) competencies conducted by a non-commercial and publicly funded European research project. Firstly, we highlight the increased prevalence of translation technologies in the translation and localisation industry, and develop upon this by reporting on survey data derived from 438 validated respondents, including freelance translators, language service providers, translator trainers, and academics. We then focus on ascertaining the prevalence of translation technology usage on a fine-grained scale to address aspects of MT, quality assessment techniques and post-editing. We report a strong need for an improvement in quality assessment methods, tools, and training, partly due to the large variance in approaches and combinations of methods, and to the lack of knowledge and resources. We note the growing uptake of MT and the perceived increase of its prevalence in future workflows. We find that this adoption of MT has led to significant changes in the human translation process, in which post-editing appears to be exclusively used for high-quality content publication. Lastly, we echo the needs of the translation industry and community in an attempt to provide a more comprehensive snapshot to inform the provision of translation training and the need for increased technical competencies.

COMPUTER-AIDED TRANSLATION AT WCC

Many individuals, companies, and government agencies need to have a large volume of foreign language printed matter translated for their use. Computer-aided translation offers the advantages of speed and volume over the normal non-assisted human translation process. With a shortage of trained language specialists, the volume of material to be translated, and the speed of translation which is desired, the computer- aided translation market becomes the most feasible and desirable option in the translation field.Weidner is one company which recognized the needs in this particular area and has developed both hardware and software to fill this need. Constant improvement and attention to detail is needed to keep such a system operating at top accuracy. It is Weidner’s goal to stay on top of all advances in the field as well as to offer a complete line of language and translation services to the community.

Towards statistical modelling of translators’ activity data

The paper discusses recent advances in human translation process research and presents a methodology for gathering and analysing translators’ activity data. We compare three translations of an English text into Danish. A coherent representation of the User Activity Data and a query formalism is suggested for retrieving source-target language alignment units and for tracing and interpreting the process data for these units. We look at a number of correction patterns and a fixation pause in more detail. With a better and more formalised way of understanding the underlying human processes, new technologies and novel ways of using existing technology could emerge that tighten the integration of speech recognition and automated translation aids into the translation workflow.

A process study of computer-aided translation

We investigate novel types of assistance for human translators, based on statistical machine translation methods. We developed the computer-aided tool Caitra that makes suggestions for sentence completion, shows word and phrase translation options, and allows postediting of machine translation output. We carried out a study of the translation process that involved non-professional translators that were native in either French or English and recorded their interaction with the tool. Users translated 192 sentences from French news stories into English. Most translators were faster and better when assisted by our tool. A detailed examination of the logs also provides insight into the human translation process, such as time spent on different activities and length of pauses.

The Monitor Model Revisited: Evidence from Process Research

Research on human translation processes to date reveals that there are many routes to successful performance and that consciousness raising helps to identify undesirable tendencies and routines. Research on translation processes also shows that expertise calls for monitoring skills and self-awareness. This paper focuses on the monitor model of translation and reports on empirical evidence that supports the model. It shows that tendencies towards literal translation emerge in the products and processes of novices and experts alike. It also argues for further research into the hypothesized literal translation automaton and its monitoring mechanism.