Translation Word-Level Auto-Completion: What Can We Achieve Out of the Box?

Proceedings of the Seventh Conference on Machine Translation (WMT), pages 1176 - 1181 December 7-8, 2022 ©2022 Association for Computational Linguistics Translation Word-Level Auto-Completion: What can we achieve out of the box? Yasmin Moslem ADAPT Centre School of Computing Dublin City University Dublin, Ireland yasmin.moslem@adaptcentre.ie Rejwanul Haque School of Computing National College of Ireland Mayor Street, IFSC Dublin, Ireland rejwanul.haque@ncirl.ie Andy Way ADAPT Centre School of Computing Dublin City University Dublin, Ireland andy.way@adaptcentre.ie Abstract Research on Machine Translation (MT) has achieved important breakthroughs in several areas. While there is much more to be done in order to build on this success, we believe that the language industry needs better ways to take full advantage of current achievements. Due to a combination of factors, including time, resources, and skills, businesses tend to apply pragmatism into their AI workflows. Hence, they concentrate more on outcomes, e.g. delivery, shipping, releases, and features, and adopt high-level working production solutions, where possible. Among the features thought to be helpful for translators are sentence-level and word-level translation auto- suggestion and auto-completion. Suggesting alternatives can inspire translators and limit their need to refer to external resources, which hopefully boosts their productivity. This work describes our submissions to WMT’s shared task on word-level auto-completion, for the Chinese-to-English, English-to-Chinese, German-to-English, and English-to-German language directions. We investigate the possibility of using pre-trained models and out-of-the-box features from available libraries. We employ random sampling to generate diverse alternatives, which reveals good results. Furthermore, we introduce our open-source API, based on CTranslate2, to serve translations, auto-suggestions, and auto- completions. 1 Introduction Translation auto-suggestion and auto-completion are among the important features that can help translators better utilize Machine Translation (MT) systems. In a Computer-Aided Translation (CAT) environment, a translator can make use of the MT word auto-suggestion feature as follows: • typing a few words, or clicking a word in a proposed MT translation, a list of suggestions is displayed, as illustrated by Figure 1. • selecting one of the word suggestions from the list, the rest of the translation is modified accordingly. The WMT’s Word-Level AutoCompletion (WLAC) shared task addresses a more specific sce- nario, where the user types a few characters, and the system predicts and auto-completes the cor- rect word, given the current context. The WLAC task even suggests that the context might be partial, and it can consist of preceding and/or following words. Given a source sequence x, typed character sequence s and a context c, WLAC aims to predict a target word w which is to be placed in the middle between the left context cl and right context cr to constitute a partial translation. Note that the last word of cl, the auto-completed word w, and the first word of cr are not necessary consecutive. Previous work proposed diverse approaches, mostly to translation sentence-level auto- suggestion and auto-completion. In their work, Li et al. (2021) proposed an approach to tackle the word-level auto-completion task. Given a tuple (x, c, s), the system decomposes the word autocompletion process …

Content truncated to 500 words