Evaluation Dataset for Zero Pronoun in Japanese to English Translation

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 356–362 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 356 ARTranslate - Immersive Language Exploration with Object Recognition and Augmented Reality Benny Platte1, Anett Platte2, Rico Thomanek1, Christian Roschke1, Tony Rolletschke1, Frank Zimmer1, Marc Ritter1 1 Technikumplatz 17, 09648 Mittweida, platte@hs-mittweida.de 2 Marschnerstraße 31, 04109 Leipzig Abstract The use of Augmented Reality in teaching and learning contexts for language is still young. The ideas are endless, the concrete educational offers available emerge only gradually. Educational opportunities that were unthinkable a few years ago are now feasible. We present a concrete realization: an executable application for mobile devices with which users can explore their environment interactively in different languages. The software recognizes up to 1000 objects in the user’s environment using a deep learning method based on Convolutional Neural Networks (CNN) and names this objects accordingly. Using Augmented Reality (AR) the objects are superimposed with 3D information in different languages. By switching the languages, the user is able to interactively discover his surrounding everyday items in all languages. The application is available as Open Source. Keywords: AR, Augmented Reality, immersive learning, language learning, deep learning, object recognition, SceneKit, CoreML 1. Introduction Language is the foundation of good communication and “one of the most important prerequisites and foundations for culture”. (Beller and Bender, 2010, p. 169). Language acquisition is regarded as the key to social integration Just as we only learn to swim in water, we can only learn to speak by speaking. Therefore there is no way around the practical usage. But how do we start? Intrinsic motivation “for its own sake, independent of factors outside the person” (Brandstätter et al., 2013) is the best one. It has to be used. Let’s take something almost everyone has with them: the smartphone (Oloruntoba, 2019). 75 % of 10-11 year olds in Germany own a smartphone. In the 12-13-year-old group there are even 95 % (Tenzer, 2019), in Switzerland 93 % (Schultz, 2018). We absorb our mother tongue immersively. Learning a non-parental second language requires effort and willingness to learn. The willingness to learn is greater if • we learn a second language as ambient language (Ru- berg et al., 2017) like for example refugees in a foreign country. “In the conditions of migration the mastery of the language of the environment marks an important step on the way of integration.” (Adler, 2011, p. 104). • the hurdle of getting us up is lowered by the simplicity of the learning context This is exactly where our contribution comes in. We lower the hurdle of engaging in a new language by using the technology of Augmented Reality (AR) to enrich the user’s environment with educational content (Fig. 1). Online Resource with Source Code https://github.com/benpla/ARTranslate Today the use of AR technology is becoming increasingly popular in engineering (Ismail et al., 2019; Rana and Patel, 2019), environmental sciences (Barreiros et al., 2016) and especially education (Sırakaya and Alsancak …

Content truncated to 500 words