Parallel feature weight decay algorithms for fast development of machine translation models

Author(s):  
Ergun Biçici
2014 ◽  
Vol 23 (12) ◽  
pp. 3101-3114
Author(s):  
Shu-Jie LIU ◽  
Chi-Ho LI ◽  
Mu LI ◽  
Ming ZHOU

2020 ◽  
Vol 13 (2) ◽  
pp. 271-285
Author(s):  
Ramunė Kasperavičienė ◽  
Jurgita Motiejūnienė ◽  
Irena Patašienė

Despite fast development of machine translation, the output quality is less than acceptable in certain language pairs. The aim of this paper is to determine the types of errors in machine translation output that cause comprehension problems to potential readers. The study is based on a reading task experiment using eye tracking and a retrospective survey as a complementary method to add more value to the research as eye tracking as a method is considered to be problematic and challenging (O’BRIEN, 2009; ALVES et al., 2009). The cognitive evaluation approach is used in an eye tracking experiment to determine the complexity of the errors in the English–Lithuanian language pair from easiest to hardest as seen by the readers of a machine-translated text. The tested parameters – gaze time and fixation count – demonstrate that a different amount of cognitive effort is required to process different types of errors in machine-translated texts. The current work aims at contributing to other research in the Translation Studies field by providing the analysis of error assessment of machine translation output.


Author(s):  
Lumin Liu

Removing undesired re ection from a single image is in demand for computational photography. Re ection removal methods are gradually effective because of the fast development of deep neural networks. However, current results of re ection removal methods usually leave salient re ection residues due to the challenge of recognizing diverse re ection patterns. In this paper, we present a one-stage re ection removal framework with an end-to-end manner that considers both low-level information correlation and efficient feature separation. Our approach employs the criss-cross attention mechanism to extract low-level features and to efficiently enhance contextual correlation. To thoroughly remove re ection residues in the background image, we punish the similar texture feature by contrasting the parallel feature separa- tion networks, and thus unrelated textures in the background image could be progressively separated during model training. Experiments on both real-world and synthetic datasets manifest our approach can reach the state-of-the-art effect quantitatively and qualitatively.


2018 ◽  
Vol 5 (1) ◽  
pp. 37-45
Author(s):  
Darryl Yunus Sulistyan

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.


Paragraph ◽  
2020 ◽  
Vol 43 (1) ◽  
pp. 98-113
Author(s):  
Michael Syrotinski

Barbara Cassin's Jacques the Sophist: Lacan, Logos, and Psychoanalysis, recently translated into English, constitutes an important rereading of Lacan, and a sustained commentary not only on his interpretation of Greek philosophers, notably the Sophists, but more broadly the relationship between psychoanalysis and sophistry. In her study, Cassin draws out the sophistic elements of Lacan's own language, or the way that Lacan ‘philosophistizes’, as she puts it. This article focuses on the relation between Cassin's text and her better-known Dictionary of Untranslatables, and aims to show how and why both ‘untranslatability’ and ‘performativity’ become keys to understanding what this book is not only saying, but also doing. It ends with a series of reflections on machine translation, and how the intersubjective dynamic as theorized by Lacan might open up the possibility of what is here termed a ‘translatorly’ mode of reading and writing.


2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.


Sign in / Sign up

Export Citation Format

Share Document