{"created":"2020-12-12T09:41:50.381365+00:00","id":6751,"links":{},"metadata":{"_buckets":{"deposit":"cd81f997-19ad-4f23-9398-64bd1830f546"},"_deposit":{"created_by":45,"id":"6751","owner":"45","owners":[45],"owners_ext":{"displayname":"","email":"dimennyaung@uit.edu.mm","username":""},"pid":{"revision_id":0,"type":"depid","value":"6751"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/00006751","sets":["1582963342780:1596102355557"]},"communities":["uit"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Developing Word-aligned Myanmar-English Parallel Corpus based on the IBM Models","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"Word alignment in bilingual corpora has been an active research\ntopic in the Machine Translation research groups. Corpus is the\nbody of text collections, which are useful for Language\nProcessing (NLP). Parallel text alignment is the identification of\nthe corresponding sentences in the parallel text. Large\ncollections of parallel level are prerequisite for many areas of\nlinguistic research. Parallel corpus helps in making statistical\nbilingual dictionary, in supporting statistical machine translation\nand in supporting as training data for word sense disambiguation\nand translation disambiguation. Nowadays, the world is a global\nnetwork and everybody will be learned more than one language.\nSo, multilingual corpora are more processing. Thus, the main\npurpose of this system is to construct word-aligned parallel\ncorpus to be able in Myanmar-English machine translation. One\nuseful concept is to identify correspondences between words in\none language and in other language. The proposed approach is\nbased on the first three IBM models and EM algorithm. It also\nshows that the approach can also be improved by using a list of\ncognates and morphological analysis."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"Word-aligned Parallel Corpus"},{"interim":"IBM Models"},{"interim":"EM Algorithm"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2020-12-12"}],"displaytype":"preview","filename":"3-Developing Word-aligned Myanmar-English Parallel Corpus based on the IBM Models.pdf","filesize":[{"value":"231 Kb"}],"format":"application/pdf","url":{"url":"https://meral.edu.mm/api/files/cd81f997-19ad-4f23-9398-64bd1830f546/3-Developing%20Word-aligned%20Myanmar-English%20Parallel%20Corpus%20based%20on%20the%20IBM%20Models.pdf"},"version_id":"f046b57c-f37b-4e04-8cbf-d8ebae4d26d4"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_journal_title":"Developing Word-aligned Myanmar-English Parallel Corpus based on the IBM Models","subitem_pages":"12-18","subitem_volume":"Volume 27– No.8"}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Khin Thandar Nwet"},{"subitem_authors_fullname":"Khin Mar Soe"},{"subitem_authors_fullname":"Ni Lar Thein"}]}]},"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":"2011-08-01"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"10.5120/3322-4566"},"item_title":"Developing Word-aligned Myanmar-English Parallel Corpus based on the IBM Models","item_type_id":"21","owner":"45","path":["1596102355557"],"publish_date":"2020-12-12","publish_status":"0","recid":"6751","relation_version_is_last":true,"title":["Developing Word-aligned Myanmar-English Parallel Corpus based on the IBM Models"],"weko_creator_id":"45","weko_shared_id":-1},"updated":"2021-12-13T03:42:46.561502+00:00"}