Morphologically Aware Word-Level Translation

Proceedings of the 28th International Conference on Computational Linguistics, pages 2847–2860 Barcelona, Spain (Online), December 8-13, 2020 2847 Morphologically Aware Word-Level Translation Paula Czarnowska1 Sebastian Ruder3 Ryan Cotterell1,2 Ann Copestake1 1University of Cambridge 3DeepMind 2ETH Z¨urich pjc211@cam.ac.uk sebastian@ruder.io ryan.cotterell@inf.ethz.ch aac10@cam.ac.uk Abstract We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning, while inflectional morphology provides additional syntactic information. This approach leads to substantial performance improvements—19% average improvement in accuracy across 6 language pairs over the state of the art in the supervised setting and 16% in the weakly supervised setting. As another contribution, we highlight issues associated with modern BLI that stem from ignoring inflectional morphology, and propose three suggestions for improving the task. 1 Introduction The ability to generalize to rare and unseen morphological variants of a known word lies at the heart of translation. For instance, a capable human Spanish–English translator would find translating the exceptionally rare form tosed (2nd person plural imperative form of ‘to cough’) as straightforward as translating the infinitive toser—despite the fact that tosed is so infrequent that many native Spanish speakers may have never encountered the form themselves. Given how basic this generalization ability is for humans, one should expect a good bilingual lexicon inducer to exhibit a similar capacity to generalize. In other words, the model should translate infrequent, regular forms of a lexeme as accurately as it translates a lexeme’s most common forms. Nevertheless, current approaches to bilingual lexicon induction (BLI) fall short of this desideratum. In a recent study, Czarnowska et al. (2019) reveal that the performance of state-of-the-art bilingual lexicon inducers degrades severely when translating less frequent inflected forms—even for the most common lexemes. The problem is severe: In the case of inducing a French–Spanish bilingual lexicon, the model of Ruder et al. (2018) correctly translates infinitives 50.6% of the time, but correctly translates the 2nd person plural imperative forms only 1.5% of the time. Motivated by this disparity, this work introduces a novel morphologically aware probability model for BLI that jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the lexeme is the core lexical unit of meaning, while inflectional morphology provides additional syntactic information on top of it (Haspelmath and Sims, 2013). It follows that we should ignore this syntactic information when translating at the word level and handle morphological inflection with a different component of the model. The empirical portion of our paper describes experiments on French, Italian and Spanish. We find our joint model substantially improves over several strong baselines on the BLI task. When evaluating on held-out lexemes,1 we observe an average performance improvement of 19% and 16% over the previous state of the art (Artetxe et al., 2018b) in the supervised and weakly supervised settings, respectively. In addition, we propose a simple …

Content truncated to 500 words