Diseño y valoración de una audioguía multilingüe y accesible

Este trabajo describe y valora el producto desarrollado en virtud de un proyecto de innovación educativa cuyo objetivo es la creación de una audioguía multilingüe, accesible e inclusiva, de la Facultad de Letras de la Universidad del País Vasco (UPV/EHU). Basada en las metodologías de aprendizaje-servicio, la audioguía es una iniciativa conjunta de los departamentos de Historia del Arte y Filología Inglesa y Alemana y Traducción e Interpretación, con la que se pretende asistir a las personas con discapacidad visual para que se muevan con seguridad a lo largo de los espacios arquitectónicos que conforman el edificio. Tras la introducción, se aborda la audiodescripción y su relación con el concepto de accesibilidad, el papel de las nuevas tecnologías en esta modalidad y las iniciativas que se han puesto en marcha sobre este tema desde los entornos formativos. A continuación, el trabajo se centra en los aspectos técnicos de la audioguía. En primer lugar, se relatan los pasos seguidos para configurar y alojar la herramienta en una página web institucional. En segundo lugar, se muestra la situación actual de dicha página web: su aspecto, el diseño elegido y la experiencia de navegación. En tercer lugar, se pretende realizar una autoevaluación del producto a partir del modelo propuesto por Conde (en prensa). El objetivo es comprobar si la audioguía a) encaja con la normativa existente al respecto y con lo que los expertos esperan de una herramienta semejante; b) funciona respecto a los objetivos con que fue creada, a partir de la experiencia de destinatarios potenciales de la misma y c) compensa a los agentes que han propiciado su creación y, en especial, al equipo del proyecto. La tecnología resulta clave para la formación de traductores e intérpretes, así como para su desempeño profesional. Los beneficios son todavía más evidentes cuando la tecnología se pone a disposición de iniciativas para mejorar la accesibilidad. Más allá de ilustrar el resultado de una experiencia concreta y de ofrecer un marco para la evaluación de la calidad de este tipo de productos, el presente trabajo podría extrapolarse a otros campos y espacios e incluso inspirar la creación de herramientas y metodologías específicas para traducir los textos audiodescritos.

English-Turkish Literary Translation Through Human-Machine Interaction

This article investigates perceptions of technology-mediated translations of literary texts by two groups: translation students and professional literary translators. The participants post-edited an excerpt from a classic Dickens novel into Turkish using a machine translation (MT) system of their choice. The analysis of the post-edited texts, participants’ answers to survey questions, and interviews with professional translators suggest that MT is currently a long way from being an essential part of any literary translation practice for the English–Turkish language pair. Translators’ interactions with MT and negative attitudes toward it may change in a positive direction as MT improves and translation practice evolves.

A Human-machine Cooperation Protocol for Machine Translation Output Edit Annotation

We report on a study exploring automatic edit annotation in a post-editing corpus with a new method for computing edit types. We examine edit type association with quality scores assigned to the machine translation output and the post-edited texts. Finally, we account for shortcomings in our method and point out edit types worth leveraging.

Communication and interactions in cloud platform subtitling

This article explores recent developments in freelance subtitling work within the audio-visual translation (AVT) industry. During the 2010s, many LSPs operating globally moved their provision of paid, professional subtitling services to cloud platforms, and I argue that such platforms, while capable of generating collaborative environments, enact information patterns which weaken the communicative and collaborative aspects of production processes, while running the risk of compromising the quality of the subtitlers’ position.

Clasificaciones de videojuegos. Una propuesta práctica para estudios empíricos

El objetivo de este artículo es ofrecer una propuesta práctica de clasificación de videojuegos que pueda contribuir a la organización coherente y homogénea de estudios empíricos sobre distintos aspectos de su localización. La propuesta se fundamenta en una revisión teórica de clasificaciones previas, especialmente, del ámbito de los Game Studies y la localización, así como en la comprobación de su utilidad mediante un estudio descriptivo realizado sobre el doblaje de videojuegos de acción-aventura. La clasificación consta de nueve géneros interactivos, según el criterio único de las destrezas empleadas en el juego, y podrá ampliarse a tantos subgéneros como tipos de juegos puedan surgir.

Subtitlers on the Cloud: The Use of Professional Web-based Systems in Subtitling Practice and Training

The bourgeoning and rapid evolution of cloud-based applications has triggered profound transformations in the audiovisual translation (AVT) mediascape. By drawing attention to the major changes that web-based ecosystems have introduced in localisation workflows, we set out to outline ways in which these new technological advances can be embedded in the AVT classroom. Along these lines, the present study sets out to explore the potential benefits of cloud platforms in AVT training curricula by exploring ways in which this technology can be exploited in subtitling training. An analysis of current subtitling practices and tools, localisation workflows, and in-demand skills in the AVT industry will be followed by an experience-based account on the use of cloud-based platforms in subtitler training environments to simulate and carry out a wide range of tasks. Our study pivots around the idea that cloud subtitling might prove useful to bridge the technological gap between academic institutions and the profession as well as to enhance the distance-learning provision of practice-oriented training in subtitling.

Evaluating the effectiveness of machine translation of audio description: the results of two pilot studies in the English-Dutch language pair

The field of translation is undergoing various profound changes. On the one hand it is being thoroughly reshaped by the advent and constant improvement of new technologies. On the other hand, new forms of translation are starting to see the light of day in the wake of social and legal developments that require that products and content that are created, are accessible for everybody. One of these new forms of translation, is audio description (AD), a service that is aimed at making audiovisual content accessible to people with sight loss. New legislation requires that this content is accessible by 2025, which constitutes a tremendous task given the limited number of people that are at present trained as audio describers. A possible solution would be to use machine translation to translate existing audio descriptions into different languages. Since AD is characterized by short sentences and simple, concrete language, it could be a good candidate for machine translation. In the present study, we want to test this hypothesis for the English-Dutch language pair. Three 30 minute AD excerpts of different Dutch movies that were originally audio described in English, were translated into Dutch using DeepL. The translations were analysed using the harmonized DQF-MQM error typology and taking into account the specific multimodal nature of the source text and the intersemiotic dimension of the original audio description process. The analysis showed that the MT output had a relatively high error rate, particularly in the categories of Accuracy – mistranslation and Fluency – grammar. This seems to indicate that extensive post-editing will be needed, before the text can be used in a professional context.

Machine translation literacy and undergraduate students in applied languages: Report on an exploratory study

This article reports on an exploratory study conducted on applied languages undergraduate students’ use of machine translation. Starting from the observation that they make extensive use of free tools available online, our aim was to understand whether they are capable of identifying and correcting machine translation errors, and if so, to what extent.

Introducing Machine Translation in the Translation Classroom: a Survey on Students’ Attitudes and Perceptions

The translation sector is going under major changes that will undoubtedly be accentuated in the future owing to the development of automation and artificial intelligence, and more specifically, of machine translation. Technology also plays a crucial role in the translation process and has a significant impact on translation competence. Therefore, it is of utmost importance that translator programs incorporate new translation technology into their curriculums in order to ensure that students are made aware of their usefulness in order to fulfil industry employment needs. This piece of research strives at mapping how and what for translation students use MT, and what are their attitudes and perceptions towards its use. Findings of a qualitative analysis indicate that undergraduate students have a positive general attitude towards MT and its many advantages, whereas they show preoccupation when MT professional issues are addressed.

What do post-editors correct? A fine-grained analysis of SMT and NMT errors

The recent improvements in neural MT (NMT) have driven a shift from statistical MT (SMT) to NMT. However, to assess the usefulness of MT models for post-editing (PE) and have a detailed insight of the output they produce, we need to analyse the most frequent errors and how they affect the task. We present a pilot study of a fine-grained analysis of MT errors based on post-editors corrections for an English to Spanish medical text translated with SMT and NMT. We use the MQM taxonomy to compare the two MT models and have a categorized classification of the errors produced. Even though results show a great variation among post-editors’ corrections, for this language combination fewer errors are corrected by post-editors in the NMT output. NMT also produces fewer accuracy errors and errors that are less critical.