Hasil untuk "Translating and interpreting"

Peter Anderson, Qi Wu, Damien Teney et al.

A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have made incredible progress in closely related areas. This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering. Both tasks can be interpreted as visually grounded sequence-to-sequence translation problems, and many of the same methods are applicable. To enable and encourage the application of vision and language methods to the problem of interpreting visually-grounded navigation instructions, we present the Matter-port3D Simulator - a large-scale reinforcement learning environment based on real imagery [11]. Using this simulator, which can in future support a range of embodied vision and language tasks, we provide the first benchmark dataset for visually-grounded natural language navigation in real buildings - the Room-to-Room (R2R) dataset1.

Paul Rosu

This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for Latin Interpretation and Translations into English for Research Assistance. Through a multi-layered translation process utilizing a fine-tuned version of GPT-4o-mini and GPT-4o, LITERA offers an unprecedented level of accuracy, showcased by greatly improved BLEU scores, particularly in classical Latin, along with improved BLEURT scores. The development of LITERA involved close collaboration with Duke University's Classical Studies Department, which was instrumental in creating a small, high-quality parallel Latin-English dataset. This paper details the architecture, fine-tuning methodology, and prompting strategies used in LITERA, emphasizing its ability to produce literal translations.

Franz Pöchhacker

This article first considers the question whether machine translation is translation and moves on to address the analogous issue for interpreting. After a review of the development and state of the art in machine interpreting, more commonly referred to as ‘spoken language translation’ or ‘speech translation’, the question of whether machine interpreting is interpreting is discussed – first with regard to terminology and conceptual distinctions and then in broader translation-theoretical frameworks. Using Otto Kade’s early definitional proposal as a point of departure, a reconceptualization is proposed in the form of a three-dimensional model designed to go beyond rigid taxonomies. The dimensions of agency, embodiment and immediacy are used to characterize translation as a graded concept in which these features may be more or less prominent.

Ralph Krüger

This paper first traces the AI-induced automation of the digitalised and datafied language industry, with a focus on neural machine translation and large language models. Then, it discusses a range of digital literacies that have become increasingly relevant in the language industry in light of these technologies, i.e., machine translation literacy, data literacy and artificial intelligence literacy. After highlighting the interface between these three literacies, the paper sketches an outline of an artificial intelligence literacy framework for translation, interpreting and specialised communication. This framework intends to capture an extensive set of competences required by stakeholders in the AI-saturated language industry.

Sijia Chen, Jan-Louis Kruger

This study investigates the visual processing patterns during computer-assisted consecutive interpreting (CACI). In phase I of the proposed CACI workflow, the interpreter listens to the source speech and respeaks it into speech recognition (SR) software. In phase II, the interpreter produces target speech supported by the SR text and its machine translation (MT) output. A group of students performed CACI with their eye movements tracked. In phase I, the participants devoted the majority of their attention to listening and respeaking, with very limited attention distributed to the SR text. However, a positive correlation was found between the percentage of dwell time on the SR text and the quality of respeaking, which suggests that active monitoring could be important. In phase II, the participants devoted more visual attention to the MT text than to the SR text and engaged in deeper and more effortful processing when reading the MT text. We identified a positive correlation between the percentage of dwell time on the MT text and interpreting quality in the L2–L1 direction but not in the L1–L2 direction. These results contribute to our understanding of computer-assisted interpreting and can provide insights for future research and training in this area.

Sijia Chen, J. Kruger

ABSTRACT Following a preliminary study that examined the potential effectiveness of a computer-assisted consecutive interpreting (CACI) mode, this paper presents a further trial of the CACI workflow. The workflow involves respeaking using speech recognition (SR) in phase I and production assisted by the SR text and its machine translation (MT) output in phase II. This study introduces a training framework for CACI that encompasses respeaking, sight translation, and post-editing. Additionally, it seeks to evaluate the CACI workflow with a group of trained students. Comparative analyses were conducted between conventional consecutive interpreting (CI) and CACI. Most of the findings from the preliminary study were successfully replicated in this study. The investigation revealed that CACI outperformed conventional CI in overall interpreting quality and accuracy in both directions of interpreting. Moreover, CACI exhibited higher fluency and lower cognitive load compared to conventional CI, albeit only in the L1–L2 direction. The quality of respeaking was found to be positively correlated with interpreting quality in both directions, underscoring the critical role of respeaking within the CACI workflow.

Yichong Huang, Baohang Li, Xiaocheng Feng et al.

Large Language models (LLMs) have exhibited remarkable abilities in understanding complex texts, offering a promising path towards human-like translation performance. However, this study reveals the misalignment between the translation-specific understanding and the general understanding inside LLMs. This understanding misalignment leads to LLMs mistakenly or literally translating some complicated concepts that they accurately comprehend in the general scenarios (e.g., QA). To align the translation-specific understanding to the general one, we propose a novel translation process, DUAT (Difficult words Understanding Aligned Translation), explicitly incorporating the general understanding on the complicated content incurring inconsistent understanding to guide the translation. Specifically, DUAT performs cross-lingual interpretation for the difficult-to-translate words and enhances the translation with the generated interpretations. Furthermore, we reframe the external tools to improve DUAT in detecting difficult words and generating helpful interpretations. We conduct experiments on the self-constructed benchmark Challenge-WMT, consisting of samples that are prone to mistranslation. Human evaluation results on high-resource and low-resource language pairs indicate that DUAT significantly facilitates the understanding alignment, which improves the translation quality (up to +3.85 COMET) and reduces the literality of the translation by -25% to -51%.

Jekaterina Maadla

This paper proposes dialogue interpreting tasks as a tool for introducing the use of the first language in language classes, and argues for integrating translatorial activities into foreign language teaching curricula. In order to test this idea six role-plays were carried out in two Estonian high schools, with Estonian as the language of instruction in one and Russian as the language of instruction in the other. The results show that without prior instruction in interpreting, high-school students demonstrated the use of interpreting strategies during role-plays involving dialogue interpreting, which suggests they possess an innate capability to translate. The author argues that the introduction of dialogue interpreting in the foreign language classroom provides students and teachers with authentic examples allowing them to compare the languages used in the plurilingual societies in which they live and study.

Olaya Martínez Sánchez

N/A

Małgorzata Tryuk

Interpreting of Children and for Children in the Actual Migration Situation in Poland The paper describes the actual scene of public service interpreting and translation in Poland since the beginning of the war in Ukraine and the influx of a vast number of Ukrainian refugees into Poland. In particular it is focused on the role played by volunteer interpreters and translators who offer linguistic and cultural assistance to Ukrainian children in medical and psychotherapeutic contexts. It also deals with the activities of non-governmental organizations offering linguistic and translational support for immigrants in Poland.

Arezu Pooryazdanpanah Kermani

The Garces model is a significant theory in the field of linguistics that focuses on the qualitative examination of translated literary works to assess the quality of translations. This approach assesses translations according to two criteria: acceptability and appropriateness. It evaluates positive and negative attributes at four different levels. The initial level of this theory focuses on analyzing the components associated with vocabulary and the transmission of meaning via language. The second level involves the analysis of syntactic and morphological components, while the third and fourth levels focus on evaluating discourse and text style. Farīd ud-Dīn ʿAṭṭār of Nishapur’s Mantiq Al-Tair is highly esteemed Persian mystical poetry that has been translated into other languages. Currently, Dr. Badi’ MohammadJomeh’s translation, which he conducted at Ain Shams University, is the most thorough of these translations. Furthermore, Mohammad Jomeh’s original translation of Mantiq Al-Tair by Attar has been praised for its self-worth in conveying the logic and invaluable ideas of the author to the Arab world. The translation is particularly notable for its precision, conciseness, eloquence, and literary highlights. As a result, it has been subjected to examination and evaluation using the Garces model and its four levels. The research findings suggest that the translator has faithfully followed the source language in the mentioned translation. Furthermore, the translation demonstrates greater acceptability and adequacy in terms of lexical and syntactic-morphological meaning compared to the other two levels. The translator's proficiency is particularly evident at these two levels. He has employed a greater number of constructive methods. However, the translation being examined has prominently featured negative tactics at two levels of discourse: functional and stylistic-semantic. This might be attributed to the choice of content for translation, specifically mystical systems. Despite incorporating culturally similar parts, the elevation of Badi’ Mohammad Jomeh’s translation can be attributed to lexical expansion, compensation, and changes in syntax and structure.Keywords: Translation Criticism, Literary translation, Mantiq Al-Tair, ʿAṭṭār of Nishapur, Badi’ Mohammad Jomeh, Carmen Garces.IntroductionMantiq Al-Tair is a highly significant oriental text that has beentranslated into various languages. Dr. Badi’ Mohammad Jomeh, anesteemed professor specializing in oriental studies at Ain ShamsUniversity, has successfully rendered a full translation of this work into the Arabic language. Evaluating the translation is vital to ensuring its accuracy, utilizing various translation principles and approaches. Translation criticism serves as a crucial connection between translation theory and translation practice. Garces's theory is a significant destination-oriented theory that consists of four stages. Due to its complete nature, it can serve as an effective model for assessing the quality of translations, particularly in the context of literary translated works, in terms of their acceptability and adequacy. This essay aims to assess the Arabic translation of Mantiq Al-Tair by Badi’ Mohammad Jomeh using Garces' methodology, employing an analytical-descriptive approach.Literature ReviewSome significant research has been conducted in the field of translation criticism, specifically regarding the translation of Mantiq Al-Tair and the application of the Garces model. Notable articles include "Mantiq Al-Tair of Attar in Lebanon (criticism on the research and translation of the Arabic Mantiq Al-Tair)" (1383) by Nik Manesh, "Criticism and review of the Persian translation of the novel Qalb al-Lil with the title Del Shab based on the model of Garces" (1396) by Ali Sayadani et al., "Lexual criticism of the translation of Sheikh Abdulhaq Mohadath Dehlavi from Fatuh al-Ghayb based on the semantic level - Garces Lexicon" (1400) by Bidkhoni and AghHosseini, "Hermeneutic view of the French translation of somemystical words of Al- Mantiq Al-Tair based on the opinions of Umberto Eco" (1400) by Moghaddam and Akrami Fard company, and "Study in Translation Al-Arabiya for the Mantiq Al-Tair" (2006) by Nadi Hassoun.It is evident that the Arabic translation of Mantiq Al-Tair has not been systematically and critically evaluated using translation criticism theories. Furthermore, the studies based on Garces theory are restricted to the translation of novels and fictional works, and despite the potential of Garces theory to assess the translation of poetic texts, no research has been conducted thus far to critique and evaluate text translations using this theory. Therefore, it is imperative to elucidate the acceptability and sufficiency of the planned translation by listing the favorable and unfavorable characteristics.Research MethodologyGarces theory is a comprehensive model used to assess literary writings. It goes beyond just the translation of words and phrases and takes into account four different levels. The Garces model is widely regarded as a prominent model for evaluating the translation of literary texts. The increasing adoption of this approach by scholars in recent years demonstrates its favorable standing among translation critics. This paradigm operates on the notion of parity between the source and destination texts. According to Garces, the source text and the translation should aim for maximum equivalence on all four levels. The four layers are: semantic-lexical, syntactic-morphological, discourse-role, and stylistic-intentional.ConclusionMantiq Al-Tair is a significant spiritual poem in Persian poetry and literature that has been translated into other languages. This essay critically evaluates the Arabic translation of . Badi’ Mohammad Jomeh’s Mantiq Al-Tair, using the Garces model as a framework for analysis. Upon evaluating this translation using the four levels of the Garces model, it was concluded that the translation being examined is in the original language. Out of the four levels in the Garces model, this translation demonstrates a higher level of conformity with the semantic-lexical level compared to the other three levels. The subgroups that have emerged in this translation at this level include assimilation, lexical expansion, lexical account, general and specific, definition and explanation, cultural equivalent, and syntactic expansion. At this stage, the translator has employed constructive methods with the exception of one instance (lexical explanation). Out of the subcategories stated, lexical expansion and lexical account are more frequent in this translation.The translation examines modifications in syntax or structure, alterations in viewpoint, compensation, implications, and the elimination of subsets at the syntactic-morphological level. Among these modifications, the change of syntax or structure is particularly prominent in this translation. In addition to implication and omission, which are negative strategies at this level, the translator has employed positive techniques. All subcategories within the two levels of discourse—functional and stylistic-semantic—are seen asnegative strategies. The most common ones are the translator's mistake and changing the function of rhetorical devices.

Mikel Artetxe, Vedanuj Goswami, Shruti Bhosale et al.

Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target languages and finetuning a multilingual model (translate-train). However, most research in the area focuses on the multilingual models rather than the MT component. We show that, by using a stronger MT system and mitigating the mismatch between training on original text and running inference on machine translated text, translate-test can do substantially better than previously assumed. The optimal approach, however, is highly task dependent, as we identify various sources of cross-lingual transfer gap that affect different tasks and approaches differently. Our work calls into question the dominance of multilingual models for cross-lingual classification, and prompts to pay more attention to MT-based baselines.

Megan Dare, Valentina Fajardo Diaz, Averie Ho Zoen So et al.

Advancements in unsupervised machine translation have enabled the development of machine translation systems that can translate between languages for which there is not an abundance of parallel data available. We explored unsupervised machine translation between Mandarin Chinese and Cantonese. Despite the vast number of native speakers of Cantonese, there is still no large-scale corpus for the language, due to the fact that Cantonese is primarily used for oral communication. The key contributions of our project include: 1. The creation of a new corpus containing approximately 1 million Cantonese sentences, and 2. A large-scale comparison across different model architectures, tokenization schemes, and embedding structures. Our best model trained with character-based tokenization and a Transformer architecture achieved a character-level BLEU of 25.1 when translating from Mandarin to Cantonese and of 24.4 when translating from Cantonese to Mandarin. In this paper we discuss our research process, experiments, and results.

C. Mellinger, Thomas A. Hanson

Renewed interest in research methods used in cognitive translation and interpreting studies (CTIS) has led to increased reflection on the nature of research and experimental design, internal and external validity, and the type and nature of experimental tasks. Of particular concern is the extent to which valid generalization can be made from empirical studies of translation, interpreting, and their associated cognitive behaviors as objects of study. This article traces the definition and history of ecological validity in the extant literature on research methods and philosophy of science, emphasizing three considerations: the experimental setting, the stimuli under investigation, and the behavioral response of participants. Subsequently, we discuss potential misunderstandings or misapplications of appeals to ecological validity, including mundane realism, naturalistic tasks, and various data collection methods. A final section describes key points to consider for research in CTIS. Throughout, the argument considers tradeoffs among various categories of validity as well as the importance of aligning experimental design with research goals. This extensive engagement with a singular aspect of validity is provided to encourage deeper reflection and better communication around the topic of ecological validity.

L. Cásedas, M. Funes, Marc Ouellet et al.

ABSTRACT Transversal competences are now essential not only for employability but for the well-being of students, and thus for society as a whole. However, these competences are not commonly taught or researched as part of higher education degree programmes. This evidently leads to a gap between ideal teaching goals and what students actually learn in their undergraduate studies. To meet this need, a psychoeducational intervention was designed and implemented in an undergraduate programme in translation and interpreting within the framework of a teaching innovation project. The impact of this intervention was tested on transversal competences such as emotional intelligence and regulation, creativity, psychological distress, and cultural intelligence, among others. This parallel exploratory study compared the effectiveness of two mindfulness-based programmes. In both mindfulness-based training programmes, the preliminary results seemed to indicate an improvement in these transversal competences. Limitations of the study were the design, sample size, and the restrictions imposed by the COVID-19 pandemic. The results of our study led to recommendations for degree programme design as well as a platform for discussion and debate on the relationship between higher education, competence-based training, and social demands. The clinical trial was registered with www.clinicaltrials.gov (NCT04392869).

Seb Dianati, Nantana Taptamat, Akiko Uchiyama et al.

The purpose of this study was to use mixed methods to examine the factors that contribute to the adoption of translation and interpreting (T&I) technologies by university instructors. The qualitative outcomes aimed to ascertain which technologies are currently being used in Australian universities, in the categories of web-search, CAT, mobile and tablet, and language lab software and hardware. An infographic was used to help display the technologies in these four domains. The findings of the quantitative analysis indicate that the frequent use of T&I technologies in instructors’ current practice significantly affected their intention to use technologies in the future. However, their experiences in both teaching and using such technologies were not factors that influenced their future use. The instructors who viewed T&I technologies favourably tended to recommend these tools to their friends and family; they believed that these tools helped them improve the accuracy of their job performance and secure their current job, and generally gave them an advantage in the employment market. At the same time, the instructors in our study faced some issues in using T&I technologies, such as the accuracy of their output and the lifespan of the software. Regardless of the challenges they faced, if an instructor perceived T&I technologies to be useful, they tended to express an intention to continue to use such technologies in the future.

Kanglong Liu, A. K. Cheung, Yufeng Liu et al.

Lisi Liang

The paper sets out to devise an online subtitling course emphasising the human nature of translation. To gain a deeper understanding of audience behaviours and attitudes towards the consumption of subtitles, the article utilises questionnaires and case studies. Results are used to devise a learner-customised and technology-assisted online course about subtitling. The case studies that inspire the course content and design include the short-video platform Douyin (the Chinese equivalent of TikTok) and the comparison of two MOOCs, Working with Translation: Theories and Practice and Consecutive Interpreting . In summary, the course design for teaching subtitling will be based on the findings of the research questions and elastically adapted to the syllabus. We put forward our course with an emphasis on the practicality of producing subtitles in light of the technological acceleration in the marketplace and, more importantly, the humanistic nature of translation.

Jemina Napier, Robert Skinner, R. Adam et al.

This article reports the findings of a nationwide sign language translator and interpreter (SLTI) census to establish a baseline description of the United Kingdom’s SLTI workforce that was commissioned by the Association of Sign Language Interpreters UK. Complete responses were received from 690 practitioners from across the United Kingdom (43% of the potential sample). The survey responses were analysed using the SPSS statistical software, specifically to look at various intersectional characteristics concerning gender, age, sexuality, race, and ethnicity. This article provides an overview of the findings with respect to two key themes: representation and diversity in the profession, along with discussion of the profile of the SLTI profession in the United Kingdom, and recommendations for actions for key stakeholder organisations. As a first snapshot, this census functions as a baseline for future comparisons, and can be modified and improved through open dialogue with professional and community groups. This snapshot helps us to identify gaps in representation. Finally, it can also inform the planning and forecasting of recruitment needs for the workforce and highlight any education and training needs.

Tianyuan Zhao, Lin Shen