@article{
 title = {Improving Named Entity Recognition for Morphologically Rich Languages Using Word Embeddings Emerging Welfare ERC Project View project Automated Neuroanatomical Relation Extraction: A Linguistically Motivated Approach with a PVT Connectivity Graph Case Stu},
 type = {article},
 year = {2014},
 identifiers = {[object Object]},
 keywords = {Czech NER,Named Entity Recognition,Skip-gram,Turkish NER,Word Embeddings},
 websites = {https://www.researchgate.net/publication/270477351},
 id = {7af456f1-d2ee-3875-a13b-c823821bafe4},
 created = {2019-10-12T09:32:39.539Z},
 file_attached = {true},
 profile_id = {56097376-c2b8-30ef-8aca-f77cc85e57a0},
 group_id = {cbcfbfec-195f-3b99-b6a1-d26e1dd80ff5},
 last_modified = {2019-10-12T10:02:42.828Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ozgur2014},
 private_publication = {false},
 abstract = {In this paper, we addressed the Named Entity Recognition (NER) problem for morphologically rich languages by employing a semi-supervised learning approach based on neural networks. We adopted a fast unsupervised method for learning continuous vector representations of words, and used these representations along with language independent features to develop a NER system. We evaluated our system for the highly inflectional Turkish and Czech languages. We improved the state-of-the-art F-score obtained for Turkish without using gazetteers by 2.26% and for Czech by 1.53%. Unlike the previous state-of-the-art systems developed for these languages, our system does not make use of any language dependent features. Therefore, we believe it can easily be applied to other morphologically rich languages.},
 bibtype = {article},
 author = {Ozgur, Arzucan and Demir, Hakan and Arzucan¨ Arzucan¨ozgür, Arzucan¨ozgür}
}

{"_id":"iW5PAQm3fNeLErnjR","bibbaseid":"ozgur-demir-arzucanarzucanozgr-improvingnamedentityrecognitionformorphologicallyrichlanguagesusingwordembeddingsemergingwelfareercprojectviewprojectautomatedneuroanatomicalrelationextractionalinguisticallymotivatedapproachwithapvtconnectivitygraphcasestu-2014","authorIDs":[],"author_short":["Ozgur, A.","Demir, H.","Arzucan¨ Arzucan¨ozgür, A."],"bibdata":{"title":"Improving Named Entity Recognition for Morphologically Rich Languages Using Word Embeddings Emerging Welfare ERC Project View project Automated Neuroanatomical Relation Extraction: A Linguistically Motivated Approach with a PVT Connectivity Graph Case Stu","type":"article","year":"2014","identifiers":"[object Object]","keywords":"Czech NER,Named Entity Recognition,Skip-gram,Turkish NER,Word Embeddings","websites":"https://www.researchgate.net/publication/270477351","id":"7af456f1-d2ee-3875-a13b-c823821bafe4","created":"2019-10-12T09:32:39.539Z","file_attached":"true","profile_id":"56097376-c2b8-30ef-8aca-f77cc85e57a0","group_id":"cbcfbfec-195f-3b99-b6a1-d26e1dd80ff5","last_modified":"2019-10-12T10:02:42.828Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"citation_key":"Ozgur2014","private_publication":false,"abstract":"In this paper, we addressed the Named Entity Recognition (NER) problem for morphologically rich languages by employing a semi-supervised learning approach based on neural networks. We adopted a fast unsupervised method for learning continuous vector representations of words, and used these representations along with language independent features to develop a NER system. We evaluated our system for the highly inflectional Turkish and Czech languages. We improved the state-of-the-art F-score obtained for Turkish without using gazetteers by 2.26% and for Czech by 1.53%. Unlike the previous state-of-the-art systems developed for these languages, our system does not make use of any language dependent features. Therefore, we believe it can easily be applied to other morphologically rich languages.","bibtype":"article","author":"Ozgur, Arzucan and Demir, Hakan and Arzucan¨ Arzucan¨ozgür, Arzucan¨ozgür","bibtex":"@article{\n title = {Improving Named Entity Recognition for Morphologically Rich Languages Using Word Embeddings Emerging Welfare ERC Project View project Automated Neuroanatomical Relation Extraction: A Linguistically Motivated Approach with a PVT Connectivity Graph Case Stu},\n type = {article},\n year = {2014},\n identifiers = {[object Object]},\n keywords = {Czech NER,Named Entity Recognition,Skip-gram,Turkish NER,Word Embeddings},\n websites = {https://www.researchgate.net/publication/270477351},\n id = {7af456f1-d2ee-3875-a13b-c823821bafe4},\n created = {2019-10-12T09:32:39.539Z},\n file_attached = {true},\n profile_id = {56097376-c2b8-30ef-8aca-f77cc85e57a0},\n group_id = {cbcfbfec-195f-3b99-b6a1-d26e1dd80ff5},\n last_modified = {2019-10-12T10:02:42.828Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n citation_key = {Ozgur2014},\n private_publication = {false},\n abstract = {In this paper, we addressed the Named Entity Recognition (NER) problem for morphologically rich languages by employing a semi-supervised learning approach based on neural networks. We adopted a fast unsupervised method for learning continuous vector representations of words, and used these representations along with language independent features to develop a NER system. We evaluated our system for the highly inflectional Turkish and Czech languages. We improved the state-of-the-art F-score obtained for Turkish without using gazetteers by 2.26% and for Czech by 1.53%. Unlike the previous state-of-the-art systems developed for these languages, our system does not make use of any language dependent features. Therefore, we believe it can easily be applied to other morphologically rich languages.},\n bibtype = {article},\n author = {Ozgur, Arzucan and Demir, Hakan and Arzucan¨ Arzucan¨ozgür, Arzucan¨ozgür}\n}","author_short":["Ozgur, A.","Demir, H.","Arzucan¨ Arzucan¨ozgür, A."],"urls":{"Paper":"https://bibbase.org/service/mendeley/1971c810-6732-3a00-9f6b-d217e1a53071/file/5e39ba4e-69a8-7f99-3852-6e2bc667ead9/full_text.pdf.pdf","Website":"https://www.researchgate.net/publication/270477351"},"bibbaseid":"ozgur-demir-arzucanarzucanozgr-improvingnamedentityrecognitionformorphologicallyrichlanguagesusingwordembeddingsemergingwelfareercprojectviewprojectautomatedneuroanatomicalrelationextractionalinguisticallymotivatedapproachwithapvtconnectivitygraphcasestu-2014","role":"author","keyword":["Czech NER","Named Entity Recognition","Skip-gram","Turkish NER","Word Embeddings"],"downloads":0},"bibtype":"article","creationDate":"2019-10-25T20:27:35.148Z","downloads":0,"keywords":["czech ner","named entity recognition","skip-gram","turkish ner","word embeddings"],"search_terms":["improving","named","entity","recognition","morphologically","rich","languages","using","word","embeddings","emerging","welfare","erc","project","view","project","automated","neuroanatomical","relation","extraction","linguistically","motivated","approach","pvt","connectivity","graph","case","stu","ozgur","demir","arzucan¨ arzucan¨ozgür"],"title":"Improving Named Entity Recognition for Morphologically Rich Languages Using Word Embeddings Emerging Welfare ERC Project View project Automated Neuroanatomical Relation Extraction: A Linguistically Motivated Approach with a PVT Connectivity Graph Case Stu","year":2014}