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

2021 ◽  
pp. 226-252
Author(s):  
Gert Vercauteren ◽  
Nina Reviers ◽  
Kim Steyaert
Keyword(s):  
Machine Translation ◽  
New Technologies ◽  
Pilot Studies ◽  
Audio Description ◽  
Sight Loss ◽  
Dutch Language ◽  
The One ◽  
Concrete Language ◽  
Constant Improvement ◽  
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.

scholarly journals COSTA MT Evaluation Tool: An Open Toolkit for Human Machine Translation Evaluation

2013 ◽  
Vol 100 (1) ◽  
pp. 83-89 ◽  
Author(s):  
Konstantinos Chatzitheodorou
Keyword(s):  
Machine Translation ◽  
Evaluation Tool ◽  
Machine Translation Evaluation ◽  
Translation Error ◽  
Mt Evaluation ◽  
Java Program ◽  
Error Classification ◽  
The One ◽  
Language Pair

Abstract A hotly debated topic in machine translation is human evaluation. On the one hand, it is extremely costly and time consuming; on the other, it is an important and unfortunately inevitable part of any system. This paper describes COSTA MT Evaluation Tool, an open stand-alone tool for human machine translation evaluation. It is a Java program that can be used to manually evaluate the quality of the machine translation output. It is simple in use, designed to allow machine translation potential users and developers to analyze their systems using a friendly environment. It enables the ranking of the quality of machine translation output segment-bysegment for a particular language pair. The benefits of this tool are multiple. Firstly, it is a rich repository of commonly used industry criteria (fluency, adequacy and translation error classification). Secondly, it is freely available to anyone and provides results that can be further analyzed. Thirdly, it estimates the time needed for each evaluated sentence. Finally, it gives suggestions about the fuzzy matching of the candidate translations.

scholarly journals Pre-Editing of Google Neural Machine Translation

2020 ◽  
Vol 10 (2) ◽  
Author(s):  
Alvin Taufik
Keyword(s):  
Machine Translation ◽  
Focus Of Attention ◽  
Source Text ◽  
Neural Machine Translation ◽  
Efficiency And Effectiveness ◽  
The One ◽  
Editing Process ◽  
Oriented Research ◽  
Language Pair ◽  
New Machine

<span>Even with the new Machine Translation (MT) platform available in Google today (Neural, as compared to the previous Statistical one in the previous years), the output is not always satisfactory. This is even more obvious in specific contexts and situations. </span><span lang="IN">Research has shown that the implementation of rules for the process prior to and the one that follows the input activities into an MT (often referred to as the pre-editing and post editing process) has proven to be fruitful (Gerlach, et. al., 2013; Shei, 2002). However, to the best knowledge of the researcher, no research on pre-editing rules on Indonesian input into MT has been conducted. This research is significant because it might increase efficiency and effectiveness of MT, especially for the language pair Indonesian-English. For that reason, t</span><span>his research intends to identify the pre-editing </span><span lang="IN">rul</span><span>es required to create a solid basis to translate Indonesian Source Text (ST) into English Target Text (TT). </span><span lang="IN">This research adopts the product-oriented research. The results show that in the pre-editing process, the length of the sentence, the conjunctions (subordinative and correlative), and the inappropriate ST words should be the focus of attention.</span>

Factored Statistical Machine Translation for German-English

2018 ◽  
Vol 5 (1) ◽  
pp. 37-45
Author(s):  
Darryl Yunus Sulistyan
Keyword(s):  
Machine Translation ◽  
English Language ◽  
Statistical Machine Translation ◽  
New Model ◽  
Language Pair

Machine Translation is a machine that is going to automatically translate given sentences in a language to other particular language. This paper aims to test the effectiveness of a new model of machine translation which is factored machine translation. We compare the performance of the unfactored system as our baseline compared to the factored model in terms of BLEU score. We test the model in German-English language pair using Europarl corpus. The tools we are using is called MOSES. It is freely downloadable and use. We found, however, that the unfactored model scored over 24 in BLEU and outperforms the factored model which scored below 24 in BLEU for all cases. In terms of words being translated, however, all of factored models outperforms the unfactored model.

English-Dogri Translation System using MOSES

2016 ◽  
Vol 1 (1) ◽  
pp. 45-49
Author(s):  
Avinash Singh ◽  
Asmeet Kour ◽  
Shubhnandan S. Jamwal
Keyword(s):  
Natural Language Processing ◽  
Machine Translation ◽  
Language Processing ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Parallel Corpus ◽  
English System ◽  
Machine Translation System ◽  
Translation Machine ◽  
Language Pair

The objective behind this paper is to analyze the English-Dogri parallel corpus translation. Machine translation is the translation from one language into another language. Machine translation is the biggest application of the Natural Language Processing (NLP). Moses is statistical machine translation system allow to train translation models for any language pair. We have developed translation system using Statistical based approach which helps in translating English to Dogri and vice versa. The parallel corpus consists of 98,973 sentences. The system gives accuracy of 80% in translating English to Dogri and the system gives accuracy of 87% in translating Dogri to English system.

The Dilemma between Aligned Expectations and Diversity in Innovation

2018 ◽  
Author(s):  
Timur Ergen
Keyword(s):  
New Technologies ◽  
Historical Case ◽  
History Of Capitalism ◽  
Synthetic Fuel ◽  
The Us ◽  
History Of ◽  
The One ◽  
Technology Policies ◽  
Lock In ◽  
Innovation Processes

This chapter brings together arguments from economics, sociology, and political economy to show that innovation processes are characterized by a dilemma between the advantages of aligned expectations—including greater coordination and investment—and those of diversity, including superior openness to new technological possibilities. To illustrate the argument, the chapter discusses a historical case involving one of the largest coordinated peace-time attempts to hasten technological innovation in the history of capitalism, namely the US energy technology policies of the 1970s and 1980s. Close examination of the commercialization of photovoltaics and synthetic fuel initiatives illustrates both sides of the dilemma between shared versus diverse expectations in innovation: coordination but possible premature lock-in on the one hand, and openness but possible stagnation on the other. The chapter shows that even the exploration and interpretation of new technologies may be as much a product of focused investment as of trial-and-error search.

scholarly journals Is There a Predisposition towards the Use of New Technologies within the Traffic Field of Emerging Countries? The Case of the Dominican Republic

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1208
Author(s):  
Francisco Alonso ◽  
Mireia Faus ◽  
Cristina Esteban ◽  
Sergio A. Useche
Keyword(s):  
Dominican Republic ◽  
Road Safety ◽  
New Technologies ◽  
Technological Development ◽  
Personal Data ◽  
Emerging Countries ◽  
Level Of Knowledge ◽  
One Year ◽  
The One ◽  
And Control

Technological devices are becoming more and more integrated in the management and control of traffic in big cities. The population perceives the benefits provided by these systems, and, therefore, citizens usually have a favorable opinion of them. However, emerging countries, which have fewer available infrastructures, could present a certain lack of trust. The objective of this work is to detect the level of knowledge and predisposition towards the use of new technologies in the transportation field of the Dominican Republic. For this study, the National Survey on Mobility was administered to a sample of Dominican citizens, proportional to the ONE census and to sex, age and province. The knowledge of ITS topics, as well as the use of mobile applications for mobility, are scarce; however, there was a significant increase that can be observed in only one year. Moreover, technology is, in general, positively assessed for what concerns the improvement of the traffic field, even though there is a lack of predisposition to provide one’s personal data, which is necessary for these devices. The process of technological development in the country must be backed up by laws that protect the citizens’ privacy. Thus, technologies that can improve road safety, mobility and sustainability can be implemented in the country.

The One-Stop Gyrification Station - Challenges and New Technologies

2021 ◽  
pp. 102111
Author(s):  
Ryan Alexander Hickmott ◽  
Abdulhameed Bosakhar ◽  
Sebastian Quezada Rojas ◽  
Mikaela Barresi ◽  
David Walker ◽  
...  
Keyword(s):  
New Technologies ◽  
One Stop ◽  
The One

Improving thai-lao neural machine translation with similarity lexicon

2021 ◽  
pp. 1-10
Author(s):  
Zhiqiang Yu ◽  
Yuxin Huang ◽  
Junjun Guo
Keyword(s):  
Machine Translation ◽  
Semantic Information ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Translation Quality ◽  
Decoder Architecture ◽  
Baseline System ◽  
Input Sentence ◽  
Resource Conditions ◽  
Language Pair

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions. Thai-Lao is a typical low-resource language pair of tiny parallel corpus, leading to suboptimal NMT performance on it. However, Thai and Lao have considerable similarities in linguistic morphology and have bilingual lexicon which is relatively easy to obtain. To use this feature, we first build a bilingual similarity lexicon composed of pairs of similar words. Then we propose a novel NMT architecture to leverage the similarity between Thai and Lao. Specifically, besides the prevailing sentence encoder, we introduce an extra similarity lexicon encoder into the conventional encoder-decoder architecture, by which the semantic information carried by the similarity lexicon can be represented. We further provide a simple mechanism in the decoder to balance the information representations delivered from the input sentence and the similarity lexicon. Our approach can fully exploit linguistic similarity carried by the similarity lexicon to improve translation quality. Experimental results demonstrate that our approach achieves significant improvements over the state-of-the-art Transformer baseline system and previous similar works.

scholarly journals TECHNOLOGIES IN CREATIVE ECONOMY AND CREATIVE SOCIETY

2015 ◽  
Vol 21 (6) ◽  
pp. 855-868 ◽  
Author(s):  
Tomas KAČERAUSKAS
Keyword(s):  
New Technologies ◽  
Communication Technologies ◽  
Creative Industries ◽  
The Other ◽  
Creative Economy ◽  
Other Hand ◽  
Political Media ◽  
The One ◽  
Media And Communication

The article deals with issues of technologies in the environment of creative economy and creative society, mostly focusing on the following topics: 1) invasion of technologies, which is accompanied by technical illiteracy or simplification of intellection presupposed by a certain technique (e.g. computers); 2) new technologies emerge in the environment dominated by consumption in order to boost consumption; 3) political, media and communication technologies are intertwined to the extent that allows us to speak about the technologized society; 4) technologies are inseparable from creative activities: on the one hand, development of technologies needs creativity, on the other hand, every branch of creative industries needs certain technologies; 5) technologic development is conditioned by their syncretism, i.e. their ability to serve the art (technē) of life and creative intentions; 6) in the creative society, happiness does not depend on constantly upgraded (i.e. consumed) technologies but is rather possible in spite of them; 7) unlimitedness is the greatest limitation of global technologies: unconnected with any existential region, they billow in the wind of ever newer technologies.

scholarly journals Economic and non-economic values and objectives in the EU’s international trade: Normative tensions, actors and processes

2019 ◽  
Author(s):  
Urszula Jaremba ◽  
Machiko Kanetake ◽  
Ingrid Koning
Keyword(s):  
Sustainable Development ◽  
Human Rights ◽  
New Technologies ◽  
Economic Values ◽  
Trade Relations ◽  
Trade Law ◽  
Law And Policy ◽  
Recent Developments ◽  
The One ◽  
The Impact

This Europe and the World: A law review special issue comprises selected papers presented at a RENFORCE workshop on the theme of tensions between the EU’s trade and non-economic values, held at Utrecht University in November 2017. The symposium addresses normative dilemmas underlying the EU’s trade law and policy. Normative dilemmas subsist between, on the one hand, the EU’s basic pursuit of its commercial interests and trade liberalization, and, on the other hand, the EU’s mandate to promote and safeguard a number of non-economic values, including human rights and sustainable development. The journal symposium aims to unveil normative tensions existing in the EU’s trade and investment policy, and understand some of the key actors and processes through which normative tensions are created and also mitigated. While the tensions between economic and non-economic values in the EU’s trade law and policy have been extensively discussed in literature, the present symposium highlights some of the recent developments in the EU’s trade relations, analyses not only human rights but also sustainable development, and examines the impact of new technologies.

Sign in / Sign up

Export Citation Format

Share Document