Improved Arabic–Chinese Machine Translation with Linguistic Input Features
This study presents linguistically augmented models of phrase-based statistical machine translation (PBSMT) using different linguistic features (factors) on the top of the source surface form. The architecture addresses two major problems occurring in machine translation, namely the poor performance...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1999-5903/11/1/22 |
| _version_ | 1818600152654413824 |
|---|---|
| author | Fares Aqlan Xiaoping Fan Abdullah Alqwbani Akram Al-Mansoub |
| author_facet | Fares Aqlan Xiaoping Fan Abdullah Alqwbani Akram Al-Mansoub |
| author_sort | Fares Aqlan |
| collection | DOAJ |
| description | This study presents linguistically augmented models of phrase-based statistical machine translation (PBSMT) using different linguistic features (factors) on the top of the source surface form. The architecture addresses two major problems occurring in machine translation, namely the poor performance of direct translation from a highly-inflected and morphologically complex language into morphologically poor languages, and the data sparseness issue, which becomes a significant challenge under low-resource conditions. We use three factors (lemma, part-of-speech tags, and morphological features) to enrich the input side with additional information to improve the quality of direct translation from Arabic to Chinese, considering the importance and global presence of this language pair as well as the limitation of work on machine translation between these two languages. In an effort to deal with the issue of the out of vocabulary (OOV) words and missing words, we propose the best combination of factors and models based on alternative paths. The proposed models were compared with the standard PBSMT model which represents the baseline of this work, and two enhanced approaches tokenized by a state-of-the-art external tool that has been proven to be useful for Arabic as a morphologically rich and complex language. The experiment was performed with a Moses decoder on freely available data extracted from a multilingual corpus from United Nation documents (MultiUN). Results of a preliminary evaluation in terms of BLEU scores show that the use of linguistic features on the Arabic side considerably outperforms baseline and tokenized approaches, the system can consistently reduce the OOV rate as well. |
| first_indexed | 2024-12-16T12:30:57Z |
| format | Article |
| id | doaj.art-821dfc66b5dd48e2a5afc4f08a7714d1 |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-12-16T12:30:57Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-821dfc66b5dd48e2a5afc4f08a7714d12022-12-21T22:31:41ZengMDPI AGFuture Internet1999-59032019-01-011112210.3390/fi11010022fi11010022Improved Arabic–Chinese Machine Translation with Linguistic Input FeaturesFares Aqlan0Xiaoping Fan1Abdullah Alqwbani2Akram Al-Mansoub3School of Information Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Information Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Information Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, South China University of Technology (SCUT), Guangzhou 510006, ChinaThis study presents linguistically augmented models of phrase-based statistical machine translation (PBSMT) using different linguistic features (factors) on the top of the source surface form. The architecture addresses two major problems occurring in machine translation, namely the poor performance of direct translation from a highly-inflected and morphologically complex language into morphologically poor languages, and the data sparseness issue, which becomes a significant challenge under low-resource conditions. We use three factors (lemma, part-of-speech tags, and morphological features) to enrich the input side with additional information to improve the quality of direct translation from Arabic to Chinese, considering the importance and global presence of this language pair as well as the limitation of work on machine translation between these two languages. In an effort to deal with the issue of the out of vocabulary (OOV) words and missing words, we propose the best combination of factors and models based on alternative paths. The proposed models were compared with the standard PBSMT model which represents the baseline of this work, and two enhanced approaches tokenized by a state-of-the-art external tool that has been proven to be useful for Arabic as a morphologically rich and complex language. The experiment was performed with a Moses decoder on freely available data extracted from a multilingual corpus from United Nation documents (MultiUN). Results of a preliminary evaluation in terms of BLEU scores show that the use of linguistic features on the Arabic side considerably outperforms baseline and tokenized approaches, the system can consistently reduce the OOV rate as well.http://www.mdpi.com/1999-5903/11/1/22Arabic morphologyfactored translation modelphrase-based machine translationpre-processingstatistical machine translation |
| spellingShingle | Fares Aqlan Xiaoping Fan Abdullah Alqwbani Akram Al-Mansoub Improved Arabic–Chinese Machine Translation with Linguistic Input Features Future Internet Arabic morphology factored translation model phrase-based machine translation pre-processing statistical machine translation |
| title | Improved Arabic–Chinese Machine Translation with Linguistic Input Features |
| title_full | Improved Arabic–Chinese Machine Translation with Linguistic Input Features |
| title_fullStr | Improved Arabic–Chinese Machine Translation with Linguistic Input Features |
| title_full_unstemmed | Improved Arabic–Chinese Machine Translation with Linguistic Input Features |
| title_short | Improved Arabic–Chinese Machine Translation with Linguistic Input Features |
| title_sort | improved arabic chinese machine translation with linguistic input features |
| topic | Arabic morphology factored translation model phrase-based machine translation pre-processing statistical machine translation |
| url | http://www.mdpi.com/1999-5903/11/1/22 |
| work_keys_str_mv | AT faresaqlan improvedarabicchinesemachinetranslationwithlinguisticinputfeatures AT xiaopingfan improvedarabicchinesemachinetranslationwithlinguisticinputfeatures AT abdullahalqwbani improvedarabicchinesemachinetranslationwithlinguisticinputfeatures AT akramalmansoub improvedarabicchinesemachinetranslationwithlinguisticinputfeatures |