Predicting Machine Translation Comprehension with a Neural Network

Comprehension of natural language translations is dependent upon several factors including textual variables (grammatical, spelling, and word choice errors, sentence complexity, etc.) and human variables (language fluency, topic knowledge, motivation, dyslexia, etc.).? An individual reader’s understanding of machine-generated translations can vary widely because of the lower accuracy usually associated with this technology. Prior studies have had mixed results in predicting which variables have the greatest influence on translation comprehension.? In the current study, we employ an artificial neural network to analyze survey responses and reading test scores, resulting in a significantly correlated forecast of reading comprehension. Thus, we are able to offer better predictions to identify which readers might have a better grasp of content from garbled translations.Comprehension of natural language translations is dependent upon several factors including textual variables (grammatical, spelling, and word choice errors, sentence complexity, etc.) and human variables (language fluency, topic knowledge, motivation, dyslexia, etc.).? An individual reader’s understanding of machine-generated translations can vary widely because of the lower accuracy usually associated with this technology. Prior studies have had mixed results in predicting which variables have the greatest influence on translation comprehension.? In the current study, we employ an artificial neural network to analyze survey responses and reading test scores, resulting in a significantly correlated forecast of reading comprehension. Thus, we are able to offer better predictions to identify which readers might have a better grasp of content from garbled translations.