MTrill: Machine Translation Impact on Language Learning

MTrill: Machine Translation Impact on Language Learning Natalia Resende School of Computing ADAPT Centre Dublin City University, Dublin, Ireland natalia.resende@adaptcentre.ie Abstract This paper presents the MTrill project which aimed at investigating the impact of popular web-based machine translation tools on the cognitive processing of English as a second language. The methodological approach and main results are presented. 1 Introduction The MTrill project was funded by the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska- Curie grant agreement No 843455. The project started on the April 25th 2019 and ended on July 16th 2021. The project aimed at investigating the impact of popular web-based machine translation (MT) tools on the cognitive processing of English as a second language. The proposed research project was motivated by the observation that students of English as a second language are using web-based MT systems as a tool to support their English learning, due to the easy access to the systems through applications on their phones which provide instant translations for the input entered either by voice, text or image. The general research question of the project was: Would the interaction with the output of the MT result in changes in the cognitive processing of English as a second language, reflected by the learning of structures seen in the output of the MT? To answer the research question, two laboratory studies were implemented in which participants © 2022 The authors. This article is licensed under a Creative Commons 3.0 licence, no derivative works, attribution, CCBY-ND recruited were tested whether they would be primed by the MT output, i.e., whether the MT system would be capable of influencing the language production of participants. The specific objectives of the experiments are listed below: 1) Investigate whether MT systems are capable of eliciting syntactic priming effects; 2) Investigate whether any priming effect elicited is of an explicit, i.e., conscious or implicit, i.e., unconscious nature. In the next section, we describe the methodological approach used in the experiments. 2 Methodology The MTrill project adopted the syntactic priming paradigm widely used behavioural method to study syntactic processing and encoding. Syntactic priming can be defined as the tendency speakers have to use a syntactic structure that has been previously encountered (Bock et al., 1989). Both experiments involved a pre-test phase, a priming test phase and an English proficiency test1. In experiment 2, a post-test phase was included. The pre-test phase was considered as the baseline, as in this phase, participants were not exposed to the MT output when translating sentences from Portuguese into English. The priming phase involved a task in which participants were requested to translate sentences from Portuguese into English using Google Translate (GT) application on their own mobile device and repeat the output out loud. Immediately after this task, they were asked to describe images in English using words provided on the screen. If participants 1 https://www.cambridgeenglish.org/test-your- english/general-english/ described the images in English using the syntactic structures previously seen in the output of the MT …

Content truncated to 500 words