{ "info": { "author": "Boris Orekhov", "author_email": "nevmenandr@gmail.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "Natural Language :: Russian", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Topic :: Text Processing :: Linguistic" ], "description": "=====================================================\n A Python LSTM-based POS-tagger for Bashkir language\n=====================================================\n\nThis module contains a utility for part-of-speech tagging of Bashkir text.\nThe tool based on LSTM neural network and takes a word order into account.\n\nInstallation\n============\n\nThe tool could be installed with pip\n\n::\n\n pip3 install bashkirtagger\n \n**Note:** the model for the utility must be downloaded separately. \nDue to limitations on the size of the project, I could not place it \non a github or PiPy. After launching the program it will download \nand unpack the model. No action is necessary on your part. But you \nwill need an Internet connection and about 50 megabytes of incoming \ntraffic.\n\n\nUsage example\n==============\n\nTagging one sentence at a time\n\n::\n\n >>> from bashkirtagger import Tagger\n >>> t = Tagger()\n >>> sentence = \"\u0411\u0435\u0440 \u043a\u0435\u0448\u0435 \u0439\u04d9\u0448\u04d9\u0439.\"\n >>> tagged_sentence = t.predict_pos(sentence)\n >>> print(tagged_sentence)\n [('\u0431\u0435\u0440', 'NUM'), ('\u043a\u0435\u0448\u0435', 'S'), ('\u0439\u04d9\u0448\u04d9\u0439', 'V')]\n \nTagging a text of several sentences\n\n::\n\n >>> from bashkirtagger import Tagger\n >>> t = Tagger()\n >>> text = \"\u0411\u0435\u0440 \u043a\u0435\u0448\u0435 \u0439\u04d9\u0448\u04d9\u0439. \u041a\u0435\u043c \u0431\u0435\u043b\u04d9.\"\n >>> tagged_text = t.text_prc(text)\n >>> print(tagged_text)\n [[('\u0431\u0435\u0440', 'NUM'), ('\u043a\u0435\u0448\u0435', 'S'), ('\u0439\u04d9\u0448\u04d9\u0439', 'V')], [(\"\u043a\u0435\u043c\", \"SPRO\"), (\"\u0431\u0435\u043b\u04d9\", \"V\")]]\n \n \nTagset\n==============\n\nTagset based on `Bashmorph morphological analyzer `_ for Bashkir language \nby Boris Orekhov.\n\n* S: substantive\n* V: verb\n* ADJ: adjective\n* NUM: numeral\n* SPRO: pronoun\n* PART: particle\n* INTJ: interjunction\n* POST: postposition\n* CONJ: conjunction\n\nSee the `paper `_ for the details.\n\nData\n==============\n\nThe model trained on collected from the web `Bashkir text corpus `_ which \nwas marked up by Bashmorph.\n\nThis tool can be used for disambiguation of rule-based markup.\n\nYou can make your own wrap of the trained model.\n\nModel's evaluation: loss: 0.0015 - acc: 0.9996 - val_loss: 0.0975 - val_acc: 0.9847.\n\n\nContacts\n==============\n\nYou can contact the contriutor of the project via email:\n\n`Boris Orekhov `_ (nevmenandr)\n\n@ gmail", "description_content_type": "", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/nevmenandr/bashkirtagger", "keywords": "nlp bashkir pos tagger", "license": "GPL", "maintainer": "", "maintainer_email": "", "name": "bashkirtagger", "package_url": "https://pypi.org/project/bashkirtagger/", "platform": "", "project_url": "https://pypi.org/project/bashkirtagger/", "project_urls": { "Homepage": "https://github.com/nevmenandr/bashkirtagger" }, "release_url": "https://pypi.org/project/bashkirtagger/0.7.0/", "requires_dist": null, "requires_python": "", "summary": "Utility for part-of-speech tagging of Bashkir text", "version": "0.7.0" }, "last_serial": 5174718, "releases": { "0.5.0": [ { "comment_text": "", "digests": { "md5": "736743ebd10fff2e95513e6525fe6509", "sha256": "c29986854d8844e554cc28fd926a71d476b0422552c9226ad98df9922571a32d" }, "downloads": -1, "filename": "bashkirtagger-0.5.0.tar.gz", "has_sig": false, "md5_digest": "736743ebd10fff2e95513e6525fe6509", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 447308, "upload_time": "2019-04-08T22:13:58", "url": "https://files.pythonhosted.org/packages/40/14/72f36955d49bf4820fa31eda6d1719306c575d32052d71b23e97550d93b3/bashkirtagger-0.5.0.tar.gz" } ], "0.6.1": [ { "comment_text": "", "digests": { "md5": "0514269b86115b502f515e896a181686", "sha256": "53fd48542cdb1bfe16d79db4fa790f10775c4162a854e426d0927ce322e3b1fb" }, "downloads": -1, "filename": "bashkirtagger-0.6.1.tar.gz", "has_sig": false, "md5_digest": "0514269b86115b502f515e896a181686", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 447462, "upload_time": "2019-04-09T11:02:11", "url": "https://files.pythonhosted.org/packages/cc/64/2bfdd8d5a3d67d4ae2858e3a52ad8cab7d244d7dae14dd71d770cafb4fde/bashkirtagger-0.6.1.tar.gz" } ], "0.6.2": [ { "comment_text": "", "digests": { "md5": "c90bb75c9f2ad00675f85bd8a06e9fe6", "sha256": "19cbb2dfe73790fdd0916f6458a397e4e094257e6d521d644d35d08bb814cffd" }, "downloads": -1, "filename": "bashkirtagger-0.6.2.tar.gz", "has_sig": false, "md5_digest": "c90bb75c9f2ad00675f85bd8a06e9fe6", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 447473, "upload_time": "2019-04-09T11:52:53", "url": "https://files.pythonhosted.org/packages/89/c0/4dfa763615dc452f8757e50684250997379c668691854c702266d21c2acc/bashkirtagger-0.6.2.tar.gz" } ], "0.7.0": [ { "comment_text": "", "digests": { "md5": "36de9c7b6459a0e143d9e840984d3898", "sha256": "697ff8a657117d0d8c6788a5fc23a3509ca028c539f5b44f206d76ab89a798d0" }, "downloads": -1, "filename": "bashkirtagger-0.7.0.tar.gz", "has_sig": false, "md5_digest": "36de9c7b6459a0e143d9e840984d3898", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 447870, "upload_time": "2019-04-22T21:56:33", "url": "https://files.pythonhosted.org/packages/e9/ad/88fcf5967258cfb4bb25079f68a90b5cbf8757783c683b6cc31e50354d30/bashkirtagger-0.7.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "36de9c7b6459a0e143d9e840984d3898", "sha256": "697ff8a657117d0d8c6788a5fc23a3509ca028c539f5b44f206d76ab89a798d0" }, "downloads": -1, "filename": "bashkirtagger-0.7.0.tar.gz", "has_sig": false, "md5_digest": "36de9c7b6459a0e143d9e840984d3898", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 447870, "upload_time": "2019-04-22T21:56:33", "url": "https://files.pythonhosted.org/packages/e9/ad/88fcf5967258cfb4bb25079f68a90b5cbf8757783c683b6cc31e50354d30/bashkirtagger-0.7.0.tar.gz" } ] }