MERAL Myanmar Education Research and Learning Portal
Item
{"_buckets": {"deposit": "5ead0de3-62be-4d1e-ae77-71bf176dc8e9"}, "_deposit": {"created_by": 73, "id": "7667", "owner": "73", "owners": [73], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "depid", "value": "7667"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/00007667", "sets": ["user-miit"]}, "communities": ["miit"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "This paper investigate the utility of unsupervised Neural Machine translation (U-NMT) on low-resource language pairs: Myanmar sign language (MSL) and Myanmar language. Since state-ofthe-art neural machine translation (NMT) require large amount of parallel sentences, which we do not have for pairs we consider. We focus primarily on incorporating two different types of monolingual data: translated Myanmar sentences of primary English and myPOS data, only into our Myanmar language side. We found that the incorporating monolingual data achieved higher performance than the baseline approach. We prepared four types of training data for U-NMT models and the results clearly show that using the myPOS corpus on incorporating the Myanmar language monolingual data achieved the\nhighest BLEU scores when compared to other training data."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Machine Translation, Neural Machine Translation, Unsupervised Neural Machine Translation, Myanmar sign language, Myanmar language"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2021-01-20"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language.pdf", "filesize": [{"value": "1.4 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_3", "mimetype": "application/pdf", "size": 1400000.0, "url": {"url": "https://meral.edu.mm/record/7667/files/Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language.pdf"}, "version_id": "51f37fd6-53bd-4289-8dca-5dc4b7448ff3"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "Issue 1", "subitem_journal_title": "Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language", "subitem_pages": "Pages 53-61", "subitem_volume": "Volume 4"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Swe Zin Moe"}, {"subitem_authors_fullname": "Ye Kyaw Thu"}, {"subitem_authors_fullname": "Hnin Aye Thant"}, {"subitem_authors_fullname": "Nandar Win Min"}, {"subitem_authors_fullname": "Thepchai Supnithi"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Journal article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2020-04-08"}, "item_title": "Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language", "item_type_id": "21", "owner": "73", "path": ["1582963674932", "1597396989070"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000007667", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-04-08"}, "publish_date": "2020-04-08", "publish_status": "0", "recid": "7667", "relation": {}, "relation_version_is_last": true, "title": ["Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language"], "weko_shared_id": -1}
Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language
http://hdl.handle.net/20.500.12678/0000007667
http://hdl.handle.net/20.500.12678/00000076672ee137a8-23ba-47a9-ba3f-0015bb746d59
5ead0de3-62be-4d1e-ae77-71bf176dc8e9
Name / File | License | Actions |
---|---|---|
![]() |
Publication type | ||||||
---|---|---|---|---|---|---|
Journal article | ||||||
Upload type | ||||||
Publication | ||||||
Title | ||||||
Title | Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language | |||||
Language | en | |||||
Publication date | 2020-04-08 | |||||
Authors | ||||||
Swe Zin Moe | ||||||
Ye Kyaw Thu | ||||||
Hnin Aye Thant | ||||||
Nandar Win Min | ||||||
Thepchai Supnithi | ||||||
Description | ||||||
This paper investigate the utility of unsupervised Neural Machine translation (U-NMT) on low-resource language pairs: Myanmar sign language (MSL) and Myanmar language. Since state-ofthe-art neural machine translation (NMT) require large amount of parallel sentences, which we do not have for pairs we consider. We focus primarily on incorporating two different types of monolingual data: translated Myanmar sentences of primary English and myPOS data, only into our Myanmar language side. We found that the incorporating monolingual data achieved higher performance than the baseline approach. We prepared four types of training data for U-NMT models and the results clearly show that using the myPOS corpus on incorporating the Myanmar language monolingual data achieved the highest BLEU scores when compared to other training data. |
||||||
Keywords | ||||||
Machine Translation, Neural Machine Translation, Unsupervised Neural Machine Translation, Myanmar sign language, Myanmar language | ||||||
Journal articles | ||||||
Issue 1 | ||||||
Unsupervised Neural Machine Translation between Myanmar Sign Language and Myanmar Language | ||||||
Pages 53-61 | ||||||
Volume 4 |