Facilitating Terminology Translation with Target Lemma Annotations

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 3105–3111 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 3105 Facilitating Terminology Translation with Target Lemma Annotations Toms Bergmanis†‡ and M¯arcis Pinnis†‡ †Tilde / Vien¯ıbas gatve 75A, Riga, Latvia ‡Faculty of Computing, University of Latvia / Rain¸a bulv. 19, Riga, Latvia {firstname.lastname}@tilde.lv Abstract Most of the recent work on terminology in- tegration in machine translation has assumed that terminology translations are given already inflected in forms that are suitable for the tar- get language sentence. In day-to-day work of professional translators, however, it is seldom the case as translators work with bilingual glos- saries where terms are given in their dictionary forms; finding the right target language form is part of the translation process. We argue that the requirement for apriori specified tar- get language forms is unrealistic and impedes the practical applicability of previous work. In this work, we propose to train machine trans- lation systems using a source-side data aug- mentation method1 that annotates randomly se- lected source language words with their tar- get language lemmas. We show that systems trained on such augmented data are readily usable for terminology integration in real-life translation scenarios. Our experiments on ter- minology translation into the morphologically complex Baltic and Uralic languages show an improvement of up to 7 BLEU points over baseline systems with no means for terminol- ogy integration and an average improvement of 4 BLEU points over the previous work. Re- sults of the human evaluation indicate a 47.7% absolute improvement over the previous work in term translation accuracy when translating into Latvian. 1 Introduction Translation into morphologically complex lan- guages involves 1) making a lexical choice for a word in the target language and 2) finding its morphological form that is suitable for the morpho- syntactic context of the target sentence. Most of the recent work on terminology translation, however, 1Relevant materials and code: https://github. com/tilde-nlp/terminology_translation has assumed that the correct morphological forms are apriori known (Hokamp and Liu, 2017; Post and Vilar, 2018; Hasler et al., 2018; Dinu et al., 2019; Song et al., 2020; Susanto et al., 2020; Dou- gal and Lonsdale, 2020). Thus previous work has approached terminology translation predominantly as a problem of making sure that the decoder’s output contains lexically and morphologically pre- specified target language terms. While useful in some cases and some languages, such approaches come short of addressing terminology translation into morphologically complex languages where each word can have many morphological surface forms. For terminology translation to be viable for trans- lation into morphologically complex languages, terminology constraints have to be soft. That is, terminology translation has to account for various natural language phenomena, which cause words to have more than one manifestation of their root morphemes. Multiple root morphemes complicate the application of hard constraint methods, such as constrained-decoding (Hokamp and Liu, 2017). That is because even after the terminology con- straint is striped from the morphemes that encode all …

Content truncated to 500 words