Click the star to add/remove an item to/from your individual schedule.
You need to be logged in to avail of this functionality,
and to see the links to virtual rooms.
Log in
- Format:
- Panel
- Location:
- Lokaal 1.13
- Sessions:
- Friday 18 August, -
Time zone: Europe/Brussels
Accepted papers:
Session 1 Friday 18 August, 2023, -Paper short abstract:
This paper advocates the use of machine translation (MT) for language instruction, with a use case study of DeepL in a Japanese class. It provides further insight into actual applications of MT for learners of Japanese, while urging teachers to explore how AI and pedagogy can coexist.
Paper long abstract:
This paper advocates the use of web-based machine translation (MT), such as DeepL or Google Translate, for language instruction and presents a use case scenario of MT in a classroom setting. MT has made tremendous strides in quality over the last several years and has a great potential to be an effective tool for language learners. Yet, many language teachers do not know how to apply MT to their classes. The paper provides further insight into actual applications of MT by presenting a use case scenario from my third-year Japanese language class.
Section 1 examines the translation quality of DeepL by using the outputs that I have collected from DeepL for the language pair of Japanese and English. DeepL’s outputs show that its quality is as good as that of human translation and therefore is suited for language instruction. Section 2 dives into my use case scenario of DeepL for my Japanese class, which involves the method called “backward translation” (S.M. Lee, 2020). I asked students to first translate their Japanese sentences into English using DeepL, and then back-translate DeepL’s English outputs into Japanese. After this process, students were instructed to compare their own writings with DeepL’s Japanese outputs and analyze the difference(s) between the two. Section 3 discusses students’ reflections on the use of DeepL. Their reflections suggest that the use of DeepL, together with the method of backward translation, not only assists their examination of grammatical errors but also enables their learning of new expressions while enhancing the meta-cognitive use of the Japanese language. Section 4 presents my concluding remarks. I argue that the advancement of AI technologies is exponential and rapid and will profoundly transform the way we teach foreign languages. I urge teachers to get ready for tsunami of AI technologies and start exploring how AI and pedagogy can be complementary.
References:
Lee, Sangmin-Michelle. “The impact of using machine translation on EFL students’ writing.” Computer Assisted Language Learning 33 (2020): 157 - 175.
Paper short abstract:
This presentation proposes a service learning project for Japanese language learners to translate the AJE newsletter using machine translation, analyzes post-editing challenges, and characterizes necessary skills to contribute to timely multilingualization for communities in need of translation.
Paper long abstract:
Machine translation has advanced dramatically with deep learning. This machine translation has already been put to practical use in situations where immediacy is required, such as municipal announcement during the Corona pandemic. On the other hand, it has been reported (Yamada 2021) that less than 1% of the content requiring translation worldwide has been translated. In order to coexist in a multilingual society, it is desirable to establish a "sustainable translation" method that enables rapid information transfer by using machine translation for content that cannot be handled by human translation. However, machine translation based on deep learning still causes "translation omissions," where part of the content of the source text is not reflected in the translated text, and mistranslations due to a lack of understanding of the context. Therefore, post-editing by human translators is considered indispensable.
On the other hand, there are many educational institutions in Europe that offer translation studies and Japanese language education classes in which students learn to translate Japanese into the local language. A learning approach, in which students participate in a community service project and enhance their academic learning, is called service learning (Kurokawa 2012). Incorporating service-learning into the classroom would allow for timely multilingualization for communities in need of translation, and for Japanese language learners to contribute to society by making use of their Japanese language skills.
Therefore, using the Japanese-English translation of the AJE newsletter as an example, this presentation will analyze what problems exist in the post-editing process of machine translation and what skills are needed to solve them, explore the conditions and work processes that should be considered if it were to be done in a classroom setting, and propose the establishment of an AJE newsletter translation project.
Kurokawa, M. (2012) ‘Service Learning in an Advanced Japanese Language Course ’ in Journal of Japanese language education153: 96-110, Association for Japanese Language Education.
Yamada, M.(2021) ‘Post-editing and a Sustainable Future for Translators’ in Journal of foreign language studies 24: 83-105, Kansai University.
Paper short abstract:
A statistical method was used to investigate the effectiveness of the automated scoring system "jWriter". The results of the survey revealed that jWriter is particularly effective at the beginner level.
Paper long abstract:
Our research group is developing a web system called "jWriter" (https://jreadability.net/jwriter/). This system is capable of automatically scoring learners' proficiency in writing and providing feedback comments to help them improve their writing. In order to clarify the validity of this system, we report the results of automatically scoring the data of 26 Japanese language learners at Y University in Croatia. The two specific research questions are as follows.
To what extent does the system "jWriter" capture the learners' operational proficiency?
To what extent do the feedback comments of the "jWriter" system affect the learners' writing?
To answer these questions, we conducted three surveys of 26 Japanese-language learners at Y University.
Survey 1: The students were asked to take the "SPOT" objective test to measure their Japanese language proficiency.
Survey 2: We asked them to write an opinion essay titled "住みやすい国の条件と理由(Conditions and reasons for a country to be a good place to live).
Survey 3: The opinion essays written in "Survey 2" were input into the "jWriter" automatic scoring system, and automatically scored. The students were then asked to rewrite their essays after receiving feedback comments from "jWriter.
As a result of analysis, the correlation coefficient between the scoring scores of Survey 1 and Survey 2 was r=.518, and the correlation coefficient between the scoring scores of Survey 1 and Survey 3 was r=.653. There was a strong correlation between the automatically scoring scores and the objective test scores both before and after the rewriting of the opinion essays. Next a Wilcoxon signed rank test was conducted on the data from Survey 2 and Survey 3, and a significant difference was found (V=72.0, p=0.015). For further analysis, we checked the data at the beginner, intermediate, and advanced levels and found significant changes, especially in the beginner data, and can therefore conclude that the automatic scoring system is particularly effective at the beginner level.