{"created":"2020-09-01T14:30:16.711739+00:00","id":4319,"links":{},"metadata":{"_buckets":{"deposit":"a205242b-5c35-4c46-97a3-c2684ebe001f"},"_deposit":{"id":"4319","owners":[],"pid":{"revision_id":0,"type":"recid","value":"4319"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/4319","sets":["1582963302567:1597824322519"]},"communities":["ucsy"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Syllable-Based Neural Named Entity Recognition for Myanmar Language","subitem_1551255648112":"en_US"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"More and more information is being created at online every day, and a lot of itis the natural language. Until recently, businesses have been unable to analyze thisdata. But advances in Natural Language Processing (NLP) make it possible to analyzeand learn from a greater range of data sources. Additionally, NLP has many centralimplications on the ways that computers and humans network on our daily life. Bypromising a bridge between human and machine, and accessing stored information,NLP plays a vital role in the multilingual society. Technologies constructed on NLPare becoming increasingly widespread.Named Entity Recognition (NER), the task of recognizing names in text andassigning those recognized Named Entities (NEs) to particular NE types such asperson name, location or organization, is a key component in many sophisticatedsystems, especially in information retrieval (IR) systems. NER for Myanmar languageis essential for the development of Myanmar NLP and it is not an easy task for manyreasons.This dissertation aims to develop Named Entity Recognition (NER) forMyanmar language as well as to promote Myanmar NLP research. Myanmar NLP issaid to be still developing and has now been struggling to be developed. In the samesituation, there are no publicly available resources that can be accessed freely orcommercially for language computation so that Myanmar is being regarded as lowresourced language. For this reason, named entity (NE) tagged corpus for MyanmarNER research is manually annotated and constructed as part of this dissertation. Theannotated NE corpus is essential for the development of Myanmar NER research.This NE tagged corpus is applied during all the conducted experiments for MyanmarNER and it will also be provided for future NER research.In written style of Myanmar language, there is no regular space betweenwords or phrases. In Myanmar language, syllables are the basic units. Thus, all theexperiments are conducted on syllable-level data instead of characters or words in thiswork.In this study, NER for Myanmar language is built by applying deep neuralnetwork architecture which can be said that Long Short-Term Memory (LSTM) -based network. The performance of neural model is also compared with baselinestatistical Conditional Random Field (CRF) model. This statistical model totallyivdepends on feature engineering. As Myanmar language is low-resourced language,named dictionary or gazetteers are not available. If these external feature resourcesare available and feature engineering is carefully done based on knowledge to coverall situations, statistical methods provide a superior result. In this work, it has beenproved that unless using additional features, deep neural networks work well onMyanmar NER and outperform baseline statistical CRF model. The best accuracy isachieved with bidirectional LSTM based network architecture. Therefore, this workeliminates the feature-engineering process and does not need to have language ordomain knowledge.The proposed syllable-based neural architecture for Myanmar NER model hasthree main layers: a character sequence layer, a syllable sequence layer, and inferencelayer. For each input syllable sequence, syllables are represented with their syllableembeddings. The character sequence layer is used to automatically extract syllablelevel features by encoding the character sequence within the syllable. ConvolutionalNeural Network (CNN) is applied to learn character sequence feature within eachinput syllable at character sequence representation layer. The syllable sequence layertakes the syllable representations as input and extracts the sentence level features,which are fed into the inference layer. For the syllable sequence representation,bidirectional LSTM is utilized to learn sentence level feature, and then CRF inferencelayer is jointly added above the network to tag the name labels. This proposedCNN_BiLSTM_CRF neural model gives the best performance out of the conductedexperiments for the Myanmar NER."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value":[]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2019-09-23"}],"displaytype":"preview","filename":"Syllable-based Neural Named Entity Recognition for Myanmar Language.pdf","filesize":[{"value":"6543 Kb"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/4319/files/Syllable-based Neural Named Entity Recognition for Myanmar Language.pdf"},"version_id":"526e101c-3cc6-4c81-9b14-b04c3cbda7a7"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"","subitem_journal_title":"","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":"University of Computer Studies, Yangon","subitem_supervisor(s)":[{"subitem_supervisor":""}]}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Mo, Hsu Myat"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Thesis"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2019-08"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"http://onlineresource.ucsy.edu.mm/handle/123456789/2258"},"item_title":"Syllable-Based Neural Named Entity Recognition for Myanmar Language","item_type_id":"21","owner":"1","path":["1597824322519"],"publish_date":"2019-09-23","publish_status":"0","recid":"4319","relation_version_is_last":true,"title":["Syllable-Based Neural Named Entity Recognition for Myanmar Language"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T00:54:24.893047+00:00"}