scholarly journals Analysis of Edit Operations for Post-editing Systems

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Jozef Kapusta ◽  
Ľubomír Benko ◽  
Dasa Munkova ◽  
Michal Munk
Keyword(s):  
Machine Translation ◽  
Morphological Analysis ◽  
Translation Research ◽  
Translation Tools ◽  
Novel Approach ◽  
Sequence Patterns ◽  
Computer Aided ◽  
Global Translation

AbstractPost-editing has become an important part not only of translation research but also in the global translation industry. While computer-aided translation tools, such as translation memories, are considered to be part of a translator's work, lately, machine translation (MT) systems have also been accepted by human translators. However, many human translators are still adopting the changes brought by translation technologies to the translation industry. This paper introduces a novel approach for seeking suitable pairs of n-grams when recommending n-grams (corresponding n-grams between MT and post-edited MT) based on the type of text (manual or administrative) and MT system used for machine translation. A tool that recommends and speeds up the correction of MT was developed to help the post-editors with their work. It is based on the analysis of words with the same lemmas and analysis of n-gram recommendations. These recommendations are extracted from sequence patterns of the mismatched words (MisMatch) between MT output and post-edited MT output. The paper aims to show the usage of morphological analysis for recommending the post-edit operations. It describes the usage of mismatched words in the n-gram recommendations for the post-edited MT output. The contribution consists of the methodology for seeking suitable pairs of words, n-grams and additionally the importance of taking into account metadata (the type of the text and/or style and MT system) when recommending post-edited operations.

scholarly journals Taking Control: Language Professionals and Their Perception of Control when Using Language Technologies

2014 ◽  
Vol 59 (2) ◽  
pp. 380-405 ◽  
Author(s):  
Elizabeth Marshman
Keyword(s):  
Machine Translation ◽  
Working Environment ◽  
Control Language ◽  
Translation Tools ◽  
Perception Of Control ◽  
Computer Aided ◽  
Language Technologies

Language technologies (for example, computer-aided and machine translation tools) are now well established in the language industry. Unfortunately, so are questions about their advantages and drawbacks. Many of these appear to be linked to language professionals’ control over their work and working environment. We surveyed these professionals to discover how they perceive language technologies’ effect on their control over the amount of work they do, the tasks they carry out and the methods they use, the quality of the product, the relationships with clients/employers, and their remuneration. The results reveal that most current users have positive opinions of technologies overall and generally feel that these tools increase their control over their work and working environment (and particularly the quantity and quality of the work). However, hesitations remain, in particular in regard to relationships with clients/employers and remuneration.

Study on Key Technique for Mechanical Engineering Based on Machine Translation

2014 ◽  
Vol 687-691 ◽  
pp. 1700-1703
Author(s):  
Chun Mei Meng ◽  
Jie Zhou
Keyword(s):  
Machine Translation ◽  
Mechanical Engineering ◽  
Paper Machine ◽  
Language Complexity ◽  
Translation Tools ◽  
Computer Aided

In this paper,machine translation and computer-aided translation are researched, in conjunction with the problems that the author encountered with the existing translation tools when translating mechanical engineering files, the necessity and idea of the mechanical engineering translation computer-aided tool brought forward. This tool aims at mechanical engineering translation features, improves speed and quality of mechanical engineering translation, ignores the language complexity and ambiguity, and introduces a mechanism of symbols for words and expressions. According to this paper, the PTCAT is designed and implemented.

scholarly journals Free/Open-Source Resources in the Apertium Platform for Machine Translation Research and Development

2010 ◽  
Vol 93 (1) ◽  
pp. 67-76 ◽  
Author(s):  
Francis Tyers ◽  
Felipe Sánchez-Martínez ◽  
Sergio Ortiz-Rojas ◽  
Mikel Forcada
Keyword(s):  
Research And Development ◽  
Open Source ◽  
Machine Translation ◽  
Morphological Analysis ◽  
Translation Research ◽  
Part Of Speech ◽  
Open Source Framework ◽  
Finite State ◽  
Translation Systems ◽  
Free Open Source

Free/Open-Source Resources in the Apertium Platform for Machine Translation Research and DevelopmentThis paper describes the resources available in the Apertium platform, a free/open-source framework for creating rule-based machine translation systems. Resources within the platform take the form of finite-state morphologies for morphological analysis and generation, bilingual transfer lexica, probabilistic part-of-speech taggers and transfer rule files, all in standardised formats. These resources are described and some examples are given of their reuse and recycling in combination with other machine translation systems.

scholarly journals Translation, from Pen-and-Paper to Computer-Assisted Tools (CAT Tools) and Machine Translation (MT)

Proceedings ◽  
2020 ◽  
Vol 63 (1) ◽  
pp. 56
Author(s):  
Bianca Han
Keyword(s):  
Machine Translation ◽  
Industry 4.0 ◽  
New Technology ◽  
Project Manager ◽  
Computer Assisted ◽  
Translation Process ◽  
Translation Tools

This paper reflects the technology-induced novelty of translation, which is perceived as a bridge between languages and cultures. We debate the extent to which the translation process maintains its specificity in the light of the new technology-enhanced working methods ensured by a large variety of Computer-Assisted Translation (CAT) and Machine Translation (MT) tools that aim to enhance the process, which includes the translation itself, the translator, the translation project manager, the linguist, the terminologist, the reviewer, and the client. This paper also hints at the topic from the perspective of the translation teacher, who needs to provide students with transversal competencies that are suitable for the digital area, supported by the ability to tackle Cloud-based translation tools, in view of Industry 4.0 requirements.

Translation Technology

2015 ◽  
Author(s):  
Lynne Bowker ◽  
Gloria Corpas Pastor
Keyword(s):  
Professional Competence ◽  
High Quality ◽  
Translation Tools ◽  
Use Of Technology ◽  
Computer Aided ◽  
Increase Productivity ◽  
Selection Of

In today’s market, the use of technology by translators is no longer a luxury but a necessity if they are to meet rising market demands for the quick delivery of high-quality texts in many languages. This chapter describes a selection of computer-aided translation tools, resources, and applications, most commonly employed by translators to help them increase productivity while maintaining high quality in their work. This chapter also considers some of the ways in which translation technology has influenced the practice and the product of translation, as well as translators’ professional competence and their preferences with regard to tools and resources.

scholarly journals Recursive Machine Translation

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Joshua Evans
Keyword(s):  
Machine Learning ◽  
Machine Translation ◽  
Literary Culture ◽  
Literary Texts ◽  
Literary Value ◽  
Translation Tools ◽  
Methodological Reflection

Machine translation tools such as Google Translate are at best seen as useful approximators, rather than offering any literary potential. In this experiment and short methodological reflection, I use Google Translate to recursively translate Austrian poet Georg Trakl’s celebrated WWI poem, ‘Grodek’, between German and English, until the two versions stabilise. I am attentive to places in which the poem and its renderings are simplified and/or literary value may be lost, but also places in which new or unexpected renderings emerge. This is a preliminary foray, but I propose that the method of recursive machine translation offers a new way to explore the translation of literary texts—a timely proposal, given the increasing applications of computer programmes and machine learning both within the humanities and throughout wider literary culture.

scholarly journals Neuron Interaction Based Representation Composition for Neural Machine Translation

2020 ◽  
Vol 34 (05) ◽  
pp. 8204-8211
Author(s):  
Jian Li ◽  
Xing Wang ◽  
Baosong Yang ◽  
Shuming Shi ◽  
Michael R. Lyu ◽  
...  
Keyword(s):  
Machine Translation ◽  
Semantic Information ◽  
Low Rank ◽  
Strong Interactions ◽  
Low Rank Approximation ◽  
Neural Machine Translation ◽  
First Order ◽  
Complex Information ◽  
Novel Approach ◽  
Rank Approximation

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better capture complex information by composing the linguistic properties embedded in individual neurons. Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e.g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors. Specifically, we leverage bilinear pooling to model pairwise multiplicative interactions among individual neurons, and a low-rank approximation to make the model computationally feasible. We further propose extended bilinear pooling to incorporate first-order representations. Experiments on WMT14 English⇒German and English⇒French translation tasks show that our model consistently improves performances over the SOTA Transformer baseline. Further analyses demonstrate that our approach indeed captures more syntactic and semantic information as expected.

scholarly journals Evaluating Machine Translations from Arabic into English and Vice Versa

2017 ◽  
Vol 3 (2) ◽  
pp. 1
Author(s):  
Riyad Al-Shalabi ◽  
Ghassan Kanaan ◽  
Huda Al-Sarhan ◽  
Alaa Drabsh ◽  
Islam Al-Husban
Keyword(s):  
Machine Translation ◽  
Word Order ◽  
Solution Structure ◽  
Sentence Length ◽  
Third Party ◽  
Abstract Machine ◽  
Translation Tools ◽  
Index Terms ◽  
Word Selection ◽  
Accuracy Degree

Abstract—Machine translation (MT) allows direct communication between two persons without the need for the third party or via dictionary in your pocket, which could bring significant and per formative improvement. Since most traditional translational way is a word-sensitive, it is very important to consider the word order in addition to word selection in the evaluation of any machine translation. To evaluate the MT performance, it is necessary to dynamically observe the translation in the machine translator tool according to word order, and word selection and furthermore the sentence length. However, applying a good evaluation with respect to all previous points is a very challenging issue. In this paper, we first summarize various approaches to evaluate machine translation. We propose a practical solution by selecting an appropriate powerful tool called iBLEU to evaluate the accuracy degree of famous MT tools (i.e. Google, Bing, Systranet and Babylon). Based on the solution structure, we further discuss the performance order for these tools in both directions Arabic to English and English to Arabic. After extensive testing, we can decide that any direction gives more accurate results in translation based on the selected machine translations MTs. Finally, we proved the choosing of Google as best system performance and Systranet as the worst one.  Index Terms: Machine Translation, MTs, Evaluation for Machine Translation, Google, Bing, Systranet and Babylon, Machine Translation tools, BLEU, iBLEU.

Sign in / Sign up

Export Citation Format

Share Document