Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929207394697216 |
|---|---|
| author | Seo, Jean Byun, Sungjoo Kang, Minha Lee, Sangah |
| author_facet | Seo, Jean Byun, Sungjoo Kang, Minha Lee, Sangah |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_17492 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data Seo, Jean Byun, Sungjoo Kang, Minha Lee, Sangah Computation and Language 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. |
| title | Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.17492 |