Personalized Machine Translation: Predicting Translational Preferences

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2019–2025, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Personalized Machine Translation: Predicting Translational Preferences Shachar Mirkin∗ IBM Research - Haifa Mount Carmel, Haifa 31905, Israel shacharm@il.ibm.com Jean-Luc Meunier Xerox Research Centre Europe 6 chemin de Maupertuis 38240 Meylan, France jean-luc.meunier@xrce.xerox.com Abstract Machine Translation (MT) has advanced in re- cent years to produce better translations for clients’ specific domains, and sophisticated tools allow professional translators to obtain translations according to their prior edits. We suggest that MT should be further personal- ized to the end-user level – the receiver or the author of the text – as done in other applica- tions. As a step in that direction, we propose a method based on a recommender systems ap- proach where the user’s preferred translation is predicted based on preferences of similar users. In our experiments, this method outper- forms a set of non-personalized methods, sug- gesting that user preference information can be employed to provide better-suited translations for each user. 1 Introduction Technologies are increasingly personalized, accommo- dating their behavior for each user. Such personaliza- tion is done through user modeling where the goal is to “get to know” the user. To that end, personalization is based on users’ attributes, such as demographics (gen- der, age etc.), personalities, and preferences. For ex- ample, in Information Retrieval, results are customized according to the user’s information and search his- tory (Speretta and Gauch, 2005), performance of Auto- matic Speech Recognition substantially improves when adapted to a specific speaker (Neumeyer et al., 1995), and Targeted Advertising makes use of the user’s loca- tion and prior purchases (K¨olmel and Alexakis, 2002). Personalization in machine translation has a some- what different nature. Providers of MT tools and ser- vices offer means to “customize” or “personalize” the translation engine for each client, mostly through do- main adaptation techniques, and a great deal of effort is made to make the human-involved translation pro- cess more efficient (see Section 2.2). Most of the focus, though, goes to customization for companies or profes- sional translators. We argue that Personalized Machine Translation (PMT below) should and can take the next step and directly address individual end-users. ∗This work was done while the first author was at Xerox Research Centre Europe. The difficulty to objectively determine whether one (automatic) translation is better than another has been repeatedly revealed in the MT literature. Our con- jecture is that one reason is individual preferences, to which we refer as Translational Preferences (TP). TP come into play both when the alternative translations are all correct, and when each of them is wrong in a different way. In the former case, a preference may be a stylistic choice, and in the latter, a matter of com- prehension or a selection of the least intolerable error in one’s opinion. For instance, one user may prefer shorter sentences than others; she may favor a more formal style, while another would rather have …

Content truncated to 500 words