{"created":"2020-09-01T15:07:04.568313+00:00","id":4576,"links":{},"metadata":{"_buckets":{"deposit":"22497a5b-ea21-4e1f-8cca-a257c7e05643"},"_deposit":{"id":"4576","owners":[],"pid":{"revision_id":0,"type":"recid","value":"4576"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/4576","sets":["1582963302567:1597824175385"]},"communities":["ucsy"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Building Large Scale Text Corpus for Joint Word Segmentation and Part-of-Speech Tagging of Myanmar Language","subitem_1551255648112":"en_US"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"In Natural Language Processing (NLP), Word segmentation and Part-of-Speech (POS) taggingare fundamental tasks. The POS information is also necessary in NLP’s preprocessing work applications suchas machine translation (MT), information retrieval (IR), etc. Currently, there are many research efforts inword segmentation and POS tagging developed separately with different methods to get high performanceand accuracy. Word segmentation and Part-of-speech tagging is one of the important actions in languageprocessing. Against this, while numerous models are provided in different languages, few works have beenperformed for Myanmar language. This paper describes the building of Myanmar Corpus to use for jointword segmentation and part-of-speech tagging of Myanmar Language. In our research, the corpus contains51207 sentences and 839161words. The corpus is created using 12 tags. To evaluate the accuracy of thecorpus, HMM model is trained on different data size and testing is done with closed test and opened test.Results with 94% accuracy in the experiments show the appropriate efficiency of the built corpus."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"Natural Language Processing"},{"interim":"POS"},{"interim":"HMM"},{"interim":"Corpus"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2020-03-12"}],"displaytype":"preview","filename":"Dim Lam Cing.pdf","filesize":[{"value":"177 Kb"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/4576/files/Dim Lam Cing.pdf"},"version_id":"15eebf66-99e1-4b00-9f85-53f3d3041fb8"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"","subitem_journal_title":"Proceedings of the 10th International Workshop on Computer Science and Engineering","subitem_pages":"","subitem_volume":""}]},"item_1583103147082":{"attribute_name":"Conference papers","attribute_value_mlt":[{"subitem_acronym":"","subitem_c_date":"","subitem_conference_title":"","subitem_part":"","subitem_place":"","subitem_session":"","subitem_website":""}]},"item_1583103211336":{"attribute_name":"Books/reports/chapters","attribute_value_mlt":[{"subitem_book_title":"","subitem_isbn":"","subitem_pages":"","subitem_place":"","subitem_publisher":""}]},"item_1583103233624":{"attribute_name":"Thesis/dissertations","attribute_value_mlt":[{"subitem_awarding_university":"","subitem_supervisor(s)":[{"subitem_supervisor":""}]}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Dim Lam, Cing"},{"subitem_authors_fullname":"Soe, Khin Mar"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Article"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2020-02-28"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"978-981-14-4787-7"},"item_title":"Building Large Scale Text Corpus for Joint Word Segmentation and Part-of-Speech Tagging of Myanmar Language","item_type_id":"21","owner":"1","path":["1597824175385"],"publish_date":"2020-03-12","publish_status":"0","recid":"4576","relation_version_is_last":true,"title":["Building Large Scale Text Corpus for Joint Word Segmentation and Part-of-Speech Tagging of Myanmar Language"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T06:18:48.414094+00:00"}