Machine translation is currently undergoing a paradigm shift from statistical to neural network models. Neural machine translation (NMT) is difficult to conceptualise for translation students, especially without context. This article describes a short in-class evaluation exercise to compare statistical and neural MT, including details of student…

Issues in computerized analysis of language usage are discussed, focusing on the problems encountered as computers, linguistics, and language teaching converge. The tools of automated language and error analysis are outlined and specific problems are illustrated in several types of classroom exercise. (MSE)

Just as learning a first language is sometimes compared to existence within the relatively sheltered world of the Garden of Eden, the process of learning a second language is viewed as analogous to survival after expulsion from the Garden into a relatively harsh world, in which the learner must come to a conscious understanding of form and meaning…

An "intelligent" system for constructing computer-assisted pattern drills to be used in second language instruction is proposed. First, some of the difficulties in designing intelligent error analysis are discussed briefly. Two major approaches to error analysis in computer-assisted instruction, pattern matching and parsing, are described, and…