Sublemma-Based Neural Machine Translation
Powerful deep learning approach frees us from feature engineering in many artificial intelligence tasks. The approach is able to extract efficient representations from the input data, if the data are large enough. Unfortunately, it is not always possible to collect large and quality data. For tasks...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/5935958 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832561418398859264 |
|---|---|
| author | Thien Nguyen Huu Nguyen Phuoc Tran |
| author_facet | Thien Nguyen Huu Nguyen Phuoc Tran |
| author_sort | Thien Nguyen |
| collection | DOAJ |
| description | Powerful deep learning approach frees us from feature engineering in many artificial intelligence tasks. The approach is able to extract efficient representations from the input data, if the data are large enough. Unfortunately, it is not always possible to collect large and quality data. For tasks in low-resource contexts, such as the Russian ⟶ Vietnamese machine translation, insights into the data can compensate for their humble size. In this study of modelling Russian ⟶ Vietnamese translation, we leverage the input Russian words by decomposing them into not only features but also subfeatures. First, we break down a Russian word into a set of linguistic features: part-of-speech, morphology, dependency labels, and lemma. Second, the lemma feature is further divided into subfeatures labelled with tags corresponding to their positions in the lemma. Being consistent with the source side, Vietnamese target sentences are represented as sequences of subtokens. Sublemma-based neural machine translation proves itself in our experiments on Russian-Vietnamese bilingual data collected from TED talks. Experiment results reveal that the proposed model outperforms the best available Russian ⟶ Vietnamese model by 0.97 BLEU. In addition, automatic machine judgment on the experiment results is verified by human judgment. The proposed sublemma-based model provides an alternative to existing models when we build translation systems from an inflectionally rich language, such as Russian, Czech, or Bulgarian, in low-resource contexts. |
| format | Article |
| id | doaj-art-3f03023756fc4488ad6ed91b51502b44 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-3f03023756fc4488ad6ed91b51502b442025-02-03T01:25:02ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/59359585935958Sublemma-Based Neural Machine TranslationThien Nguyen0Huu Nguyen1Phuoc Tran2Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, VietnamFaculty of Information Technology, Ho Chi Minh City University of Food Industry, Ho Chi Minh City, VietnamNatural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, VietnamPowerful deep learning approach frees us from feature engineering in many artificial intelligence tasks. The approach is able to extract efficient representations from the input data, if the data are large enough. Unfortunately, it is not always possible to collect large and quality data. For tasks in low-resource contexts, such as the Russian ⟶ Vietnamese machine translation, insights into the data can compensate for their humble size. In this study of modelling Russian ⟶ Vietnamese translation, we leverage the input Russian words by decomposing them into not only features but also subfeatures. First, we break down a Russian word into a set of linguistic features: part-of-speech, morphology, dependency labels, and lemma. Second, the lemma feature is further divided into subfeatures labelled with tags corresponding to their positions in the lemma. Being consistent with the source side, Vietnamese target sentences are represented as sequences of subtokens. Sublemma-based neural machine translation proves itself in our experiments on Russian-Vietnamese bilingual data collected from TED talks. Experiment results reveal that the proposed model outperforms the best available Russian ⟶ Vietnamese model by 0.97 BLEU. In addition, automatic machine judgment on the experiment results is verified by human judgment. The proposed sublemma-based model provides an alternative to existing models when we build translation systems from an inflectionally rich language, such as Russian, Czech, or Bulgarian, in low-resource contexts.http://dx.doi.org/10.1155/2021/5935958 |
| spellingShingle | Thien Nguyen Huu Nguyen Phuoc Tran Sublemma-Based Neural Machine Translation Complexity |
| title | Sublemma-Based Neural Machine Translation |
| title_full | Sublemma-Based Neural Machine Translation |
| title_fullStr | Sublemma-Based Neural Machine Translation |
| title_full_unstemmed | Sublemma-Based Neural Machine Translation |
| title_short | Sublemma-Based Neural Machine Translation |
| title_sort | sublemma based neural machine translation |
| url | http://dx.doi.org/10.1155/2021/5935958 |
| work_keys_str_mv | AT thiennguyen sublemmabasedneuralmachinetranslation AT huunguyen sublemmabasedneuralmachinetranslation AT phuoctran sublemmabasedneuralmachinetranslation |