We present in this article what we believe to be one of the first attempts at video game machine translation. Our study shows that models trained only with limited in-domain data surpass publicly available systems by a significant margin, and a subsequent human evaluation reveals interesting findings in the final translation. The first part of the article introduces some of the challenges of video game translation, some of the existing literature, as well as the systems and data sets used in this experiment. The last sections discuss our analysis of the resulting translation and the potential benefits of such an automated system. One such finding highlights the model's ability to learn typical rules and patterns of video game translations from English into French. Our conclusions therefore indicate that the specific case of video game machine translation could prove very much useful given the encouraging results, the highly repetitive nature of the work, and the often poor working conditions that translators face in this field. As with other use cases of MT in cultural sectors, however, we believe this is heavily dependent on the proper implementation of the tool, which should be used interactively by human translators to stimulate creativity instead of raw post-editing for the sake of productivity.
翻译:我们在这个文章中展示了我们认为是首次尝试电子游戏机器翻译的图案。我们的研究显示,仅以有限的域内数据培训的模型大大超过公开提供的系统,随后的人类评价揭示了最后翻译中有趣的结果。文章第一部分介绍了电子游戏翻译的一些挑战,一些现有文献,以及本实验中使用的系统和数据集。最后几节讨论了我们对由此产生的翻译的分析以及这种自动化系统的潜在好处。其中一项发现突出显示了该模型学习从英语到法语的视频游戏翻译的典型规则和模式的能力。因此,我们的结论表明,鉴于令人鼓舞的结果、工作的高度重复性质以及翻译在这一领域所面临的通常恶劣的工作条件,视频游戏机器翻译的具体案例可以证明非常有用。然而,与文化部门中MT的其他使用案例一样,我们认为这在很大程度上取决于该工具的适当应用,人类翻译应当以互动的方式利用该工具来激发创造力,而不是为了生产力而原始的后期编辑。