{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/application-of-a-hybrid-bi-lstm-crf-model-to","title":"Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition","arxiv_id":"1709.09686","date":"2017-09-27","proceeding":null,"authors":["L. T. Anh","M. Y. Arkhipov","M. S. Burtsev"],"abstract":"Named Entity Recognition (NER) is one of the most common tasks of the natural\nlanguage processing. The purpose of NER is to find and classify tokens in text\ndocuments into predefined categories called tags, such as person names,\nquantity expressions, percentage expressions, names of locations,\norganizations, as well as expression of time, currency and others. Although\nthere is a number of approaches have been proposed for this task in Russian\nlanguage, it still has a substantial potential for the better solutions. In\nthis work, we studied several deep neural network models starting from vanilla\nBi-directional Long Short-Term Memory (Bi-LSTM) then supplementing it with\nConditional Random Fields (CRF) as well as highway networks and finally adding\nexternal word embeddings. All models were evaluated across three datasets:\nGareev's dataset, Person-1000, FactRuEval-2016. We found that extension of\nBi-LSTM model with CRF significantly increased the quality of predictions.\nEncoding input tokens with external word embeddings reduced training time and\nallowed to achieve state of the art for the Russian NER task.","url_abs":"http://arxiv.org/abs/1709.09686v2","url_pdf":"http://arxiv.org/pdf/1709.09686v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"application-of-a-hybrid-bi-lstm-crf-model-to","repo_url":"https://github.com/deepmipt/DeepPavlov","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"application-of-a-hybrid-bi-lstm-crf-model-to","repo_url":"https://github.com/deepmipt/ner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"crf","method_name":"CRF"},{"method_slug":"highway-networks","method_name":"Highway networks"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}