Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data
This work addresses the preservation of the endangered Manchu language by enabling translation to Korean, though it is incremental as it applies existing methods to a new language pair.
The authors tackled the problem of Manchu-Korean machine translation by developing Mergen, the first model for this language pair, using augmented data from historical texts and dictionaries, resulting in a 20-30 point BLEU score improvement.
The Manchu language, with its roots in the historical Manchurian region of Northeast China, is now facing a critical threat of extinction, as there are very few speakers left. In our efforts to safeguard the Manchu language, we introduce Mergen, the first-ever attempt at a Manchu-Korean Machine Translation (MT) model. To develop this model, we utilize valuable resources such as the Manwen Laodang(a historical book) and a Manchu-Korean dictionary. Due to the scarcity of a Manchu-Korean parallel dataset, we expand our data by employing word replacement guided by GloVe embeddings, trained on both monolingual and parallel texts. Our approach is built around an encoder-decoder neural machine translation model, incorporating a bi-directional Gated Recurrent Unit (GRU) layer. The experiments have yielded promising results, showcasing a significant enhancement in Manchu-Korean translation, with a remarkable 20-30 point increase in the BLEU score.