Browsing Research Institute in Information and Language Processing by Authors
Knowledge distillation for quality estimationGajbhiye, Amit; Fomicheva, Marina; Alva-Manchego, Fernando; Blain, Frederic; Obamuyide, Abiola; Aletras, Nikolaos; Specia, Lucia (Association for Computational Linguistics, 2021-12-31)Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent success in QE stems from the use of multilingual pre-trained representations, where very large models lead to impressive results. However, the inference time, disk and memory requirements of such models do not allow for wide usage in the real world. Models trained on distilled pre-trained representations remain prohibitively large for many usage scenarios. We instead propose to directly transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. We show that this approach, in combination with data augmentation, leads to light-weight QE models that perform competitively with distilled pre-trained representations with 8x fewer parameters.
Unsupervised quality estimation for neural machine translationFomicheva, Marina; Sun, Shuo; Yankovskaya, Lisa; Blain, Frédéric; Guzmán, Francisco; Fishel, Mark; Aletras, Nikolaos; Chaudhary, Vishrav; Specia, Lucia (Association for Computational Linguistics, 2020-09-01)Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time. Existing approaches require large amounts of expert annotated data, computation and time for training. As an alternative, we devise an unsupervised approach to QE where no training or access to additional resources besides the MT system itself is required. Different from most of the current work that treats the MT system as a black box, we explore useful information that can be extracted from the MT system as a by-product of translation. By employing methods for uncertainty quantification, we achieve very good correlation with human judgments of quality, rivalling state-of-the-art supervised QE models. To evaluate our approach we collect the first dataset that enables work on both black-box and glass-box approaches to QE.