Towards a machine learning approach to the analysis of indirect translation

Ustaszewski, Michael

doi:10.1080/14781700.2021.1894226

Cited by 11 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study uses machine learning methodology [19] as a computational technique based on the Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Naïve Bayes Classification (NBC) algorithms. Previous studies have shown that machine learning is a relevant approach in text mining [20].…”

Section: Methodsmentioning

confidence: 99%

Sentiment Analysis of Customer Feedback Reviews Towards Hotel’s Products and Services in Labuan Bajo

Christanto

Singgalen

2022

Journal-ISI

View full text Add to dashboard Cite

The feedback review column on the TripAdvisor website can process the sentiment analysis by classifying the positive and negative impressions of the consumer using machine learning, namely text mining. This study analyzes consumer sentiment for hotel products and services in Labuan Bajo based on feedback review data on the TripAdvisor website. Meanwhile, the algorithm used is Nave Bayes Classifier (NBC), Support Vector Machine (SVM), also SMOTE Upsampling for the k-Nearest Neighbor (k-NN) algorithm. The classification result shows 702 negative feedback reviews and 2531 positive feedback reviews. The evaluation of algorithm performance shows the accuracy of SVM is 78,30% and NBC is 78,29% compared with k-NN with 85,24% accuracy, using SMOTE Upsampling with a class precision description of 100% prediction negative (1784 true Neg & 0 true Pos) and 77,21% prediction positive (747 true Neg & 2531 true Pos). The class recall description also shows 70,49% true Negative (1784 pred Neg & 747 pred Pos) and 100% true Positive (0 pred Neg & 2531 pred Pos). These findings indicate that the k-NN algorithm shows the best result instead of the SVM and NBC algorithm, according to the sentiment analysis result of customer feedback reviews on hotel products and services in Labuan Bajo through TripAdvisor website.

show abstract

Section: Methodsmentioning

confidence: 99%

Sentiment Analysis of Customer Feedback Reviews Towards Hotel’s Products and Services in Labuan Bajo

Christanto

Singgalen

2022

Journal-ISI

View full text Add to dashboard Cite

show abstract

“…A growing interest in using machine learning-based approaches has emerged to predict task types correlated with cognitive loading ( Ayres and Paas, 2012 ). However, in CTIS, very limited research has been done to apply machine-based learning approaches to analyze empirical data associated with translation and interpreting tasks, with only very few exceptions (e.g., Baroni and Bernardini, 2006 , related to translation, Michael et al, 2020 , related to the use of machine translation, Ustaszewski, 2021 , related to indirect translation), alongside conceptual discussions on how machine translation and machine learning can inform each other (see Schaeffer et al, 2020 ; O’brien, 2022 ). Still, whether or not machine learning-based approaches have the potential to be adequately used in the translation and interpreting field to more accurately predict the task type correlating with cognitive loading has yet to be explored and verified.…”

Section: Research Backgroundmentioning

confidence: 99%

Translation directionality and the Inhibitory Control Model: a machine learning approach to an eye-tracking study

Chang

Chen

2023

Front. Psychol.

View full text Add to dashboard Cite

IntroductionBased on such physiological data as pupillometry collected in an eye-tracking experiment, the study has further confirmed the effect of directionality on cognitive loads during L1 and L2 textual translations by novice translators, a phenomenon called “translation asymmetry” suggested by the Inhibitory Control Model, while revealing that machine learning-based approaches can be usefully applied to the field of Cognitive Translation and Interpreting Studies.MethodsDirectionality was the only factor guiding the eye-tracking experiment where 14 novice translators with the language combination of Chinese and English were recruited to conduct L1 and L2 translations while their pupillometry were recorded. They also filled out a Language and Translation Questionnaire with which categorical data on their demographics were obtained.ResultsA nonparametric related-samples Wilcoxon signed rank test on pupillometry verified the effect of directionality, suggested by the model, during bilateral translations, verifying “translation asymmetry” at a textual level. Further, using the pupillometric data, together with the categorical information, the XGBoost machine-learning algorithm yielded a model that could reliably and effectively predict translation directions.ConclusionThe study has shown that translation asymmetry suggested by the model was valid at a textual level, and that machine learning-based approaches can be gainfully applied to Cognitive Translation and Interpreting Studies.

show abstract

“…Thus, this research explored the MT system's ability to translate terminology in the Information Technology domain from English to the low resource language of Persian by comparing the application of two types of translation techniques' (static and instance selection) postediting. This provided the opportunity to manually evaluate by checking and comparing their performance (Ustaszewski, 2021).…”

Section: Introductionmentioning

confidence: 99%

Neural Machine Translation and Post-editing: Improving translation of domain specific English terms for a low resource language

Asadi,

Shokpour,

O'Neill

et al. 2023

Preprint

View full text Add to dashboard Cite

Neural Machine Translation (NMT) has demonstrated salient enhancement and quality output in various aspects, but issues remain when translating specific terms across domains when data are heterogeneous or dealing with rare phrases. To explore this, the translation system for the language pair: English and Persian, was considered, since low resource languages like Persian require more effort and attention to provide accurate translation when dealing with texts in specific domains. An aligned parallel terminology database was created in the Information Technology domain, where all terms were manually annotated. Data were selected from a collection of parallel sentences from the OPUS repository. Terms in the source and the target language were identified and annotated manually. After training an NMT model, the system was manually evaluated on the effectiveness of the application of instance selection to retrieve sentences. Its use led to an overall enhancement in post-editing, thereby achieving a better translation. Besides gaining insights into errors and system performance, this method provides guidance for setting priorities for future extensions and improvements for machine translation. It also sheds light on the use of instance selection across different scenarios in relation to low resource languages like Persian to achieve an overall high quality term translation accuracy.

show abstract

Towards a machine learning approach to the analysis of indirect translation

Cited by 11 publications

References 31 publications

Sentiment Analysis of Customer Feedback Reviews Towards Hotel’s Products and Services in Labuan Bajo

Sentiment Analysis of Customer Feedback Reviews Towards Hotel’s Products and Services in Labuan Bajo

Translation directionality and the Inhibitory Control Model: a machine learning approach to an eye-tracking study

Neural Machine Translation and Post-editing: Improving translation of domain specific English terms for a low resource language

Contact Info

Product

Resources

About