The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation (NMT). Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student model. However, KD approaches to Transformer architecture often rely on heuristics, particularly when deciding which teacher layers to distill from. In this paper, we introduce the “Align-to-Distill” (A2D) strategy, designed to address the feature mapping problem by adaptively aligning student attention heads with their teacher counterparts during training. The Attention Alignment Module (AAM) in A2D performs a dense head-by-head comparison between student and teacher attention heads across layers, turning the combinatorial mapping heuristics into a learning problem. Our experiments show the efficacy of A2D, demonstrating gains of up to +3.61 and +0.63 BLEU points for WMT-2022 De→Dsb and WMT-2014 En→De, respectively, compared to Transformer baselines.The code and data are available at https://github.com/ncsoft/Align-to-Distill.

Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, Jaegul Choo. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

The demand for computer-assisted language learning systems that can provide corrective feedback on language learners’ speaking has increased. However, it is not a trivial task to detect grammatical errors in oral conversations because of the unavoidable errors of automatic speech recognition systems. To provide corrective feedback, a novel method to detect grammatical errors in speaking performance is proposed. The proposed method consists of two sub-models: the grammaticality-checking model and the error-type classification model. We automatically generate grammatical errors that learners are likely to commit and construct error patterns based on the articulated errors. When a particular speech pattern is recognized, the grammaticality-checking model performs a binary classification based on the similarity between the error patterns and the recognition result using the confidence score. The error-type classification model chooses the error type based on the most similar error pattern and the error frequency extracted from a learner corpus. The grammaticality checking method largely outperformed the two comparative models by 56.36% and 42.61% in F-score while keeping the false positive rate very low. The error-type classification model exhibited very high performance with a 99.6% accuracy rate. Because high precision and a low false positive rate are important criteria for the language-tutoring setting, the proposed method will be helpful for intelligent computer-assisted language learning systems.

This study introduces the speech and language technologies used in the educational assistant robots that we developed for language learning and exploring the affective effects of robot-assisted language learning (RALL). To achieve this purpose, a course was designed in which students have meaningful interaction with intelligent robots in an immersive environment. A total of 24 elementary students, ranging in age over 9-13, were enrolled in English lessons. Descriptive statistics and pre-test/post-test design were used to investigate the affective effects of RALL approach. The result showed that RALL is promoting and improving students' satisfaction, interest, confidence, and motivation at the significance level of 0.01.