{
    "info": {
        "author": "Henry Rosales",
        "author_email": "hrosmendez@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Education",
            "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.4",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: 3.7",
            "Topic :: Software Development :: Build Tools"
        ],
        "description": "# Word Sense Disambiguation wrapper\n\nIn natural language processing **word sense disambiguation** (WSD) is the problem of determining which \"sense\" (meaning) of a word is activated by the use of the word in a particular context, a process which appears to be largely unconscious in people.\n\nThis is a simple library that wrap two WSD methods: NLTK and Babelfy. \n\n## Requirements\nYou should run \n```bash\npip3 install xmltodict\npip3 install nltk\npip3 install pywsd\n```\nThe NLTK library requires more extra configurations, see this [link](https://pythonprogramming.net/installing-nltk-nlp-python/) to more details.\n\n## Methods\nThe ```wsdNLTK``` methods call the function ```pywsd.disambiguate``` which returns a mapping between words of the input text and their WornNet Synsets. \n```python\nwsd = WrapperWSD()\nwsd.wsdNLTK(u'My sister has a dog. She loves him.')\n#output: [('sister', Synset('sister.n.02'), 3, 9), ('dog', Synset('pawl.n.01'), 16, 19), ('loves', Synset('sleep_together.v.01'), 25, 30)]\n```\n\nInstead of returning the WornNet Synsets, the method ```wsdNLTK_offset``` returns a mapping between words of the input text and their WornNet offset.  \n\n```python\nwsd.wsdNLTK_offset(u'My sister has a dog. She loves him.')\n#output: [('president', 597265, 21, 30), ('USA', 8394922, 38, 41), ('best', 67379, 54, 58)]\n```\n\nA mapping between WordNet and Wikipedia was proposed in  **[Miller et al]** available for download [here](https://www.informatik.tu-darmstadt.de/media/ukp/data/fileupload_2/lexical_resources/MillerGurevych2014_alignment.tar_1.zip).  In the next example you can see some key-values of it.\n\n```python\nwd2wiki = {\n 1740: 'https://en.wikipedia.org/wiki/Madison_Square_Garden,_L.P.',\n 2137: 'https://en.wikipedia.org/wiki/Abstraction',\n 2452: 'https://en.wikipedia.org/wiki/Object_(philosophy)',\n 2684: 'https://en.wikipedia.org/wiki/Computer_file',\n 3553: 'https://en.wikipedia.org/wiki/Unit_of_alcohol',\n ...\n }\n```\n\nWe used this mapping to link entities from Wikipedia for those cases where exists a correspondence.\n\n```python\nwsd.wsdNLTK_links(u'My sister has a dog. She loves him.')\n#output: [{'start': 38, 'end': 41, 'label': 'USA', 'link': 'United_States_Army'}]\n```\n\nOn the other hand, we include Babelfy targetting BabelSynsets\n```python\nwsd.wsdBabelfy(u'My sister has a dog. She loves him.')\n#output: [('sister', 'bn:00071838n', 3, 9), ('dog', 'bn:00015267n', 16, 19), ('loves', 'bn:00090504v', 25, 30)]\n```\n\n\n## Combining the output with Entity Linking\n\nYou can use the [nifwrapper](https://github.com/henryrosalesmendez/nifwrapper) library in order to merge the WSD outputs with Entity Linking annotations.\n\n```python\nfrom wrapperWSD import WrapperWSD\nfrom nifwrapper import *\n\n\n#---- Obtaining disambiguation\nwsd = WrapperWSD()\ncorefWSD = wsd.wsdNLTK_links(u'My sister has a dog. She loves him.')\nprint(\"corefWSD:\",corefWSD)\n#output: [('sister', Synset('sister.n.02'), 3, 9), ('dog', Synset('pawl.n.01'), 16, 19), ('loves', Synset('sleep_together.v.01'), 25, 30)]\n\n\n#---- Obtaining Entity Linking results\n# inline NIF corpus creation\nwrp = NIFWrapper()\ndoc = NIFDocument(\"https://example.org/doc1\")\n#--\nsent = NIFSentence(\"https://example.org/doc1#char=0,19\")\nsent.addAttribute(\"nif:beginIndex\",\"0\",\"xsd:nonNegativeInteger\")\nsent.addAttribute(\"nif:endIndex\",\"19\",\"xsd:nonNegativeInteger\")\nsent.addAttribute(\"nif:isString\",\"My sister has a dog.\",\"xsd:string\")\nsent.addAttribute(\"nif:broaderContext\",[\"https://example.org/doc1\"],\"URI LIST\")\n\n\n#-- \na1 = NIFAnnotation(\"https://example.org/doc1#char=3,9\", \"3\", \"9\", [\"https://en.wikipedia.org/wiki/Sibling\"], [\"dbo:FamilyRelations\"])\na1.addAttribute(\"nif:anchorOf\",\"sister\",\"xsd:string\")\nsent.pushAnnotation(a1)\ndoc.pushSentence(sent)\n\n#--\nsent2 = NIFSentence(\"https://example.org/doc1#char=21,35\")\nsent2.addAttribute(\"nif:isString\",\"She loves him.\",\"xsd:string\")\nsent2.addAttribute(\"nif:broaderContext\",[\"https://example.org/doc1\"],\"URI LIST\")\nsent2.addAttribute(\"nif:beginIndex\",\"21\",\"xsd:nonNegativeInteger\")\nsent2.addAttribute(\"nif:endIndex\",\"35\",\"xsd:nonNegativeInteger\")\ndoc.pushSentence(sent2)\n#--\nwrp.pushDocument(doc)\n\n#---- Combining EL annotations with coreferences \nwrp.extendsDocWithWSD(corefWSD, doc.uri)\nprint(wrp.toString())\n```\n\n\n\n\n## Reference\n\n**[Miller et al]**  *WordNet\u2013Wikipedia\u2013Wiktionary: Construction of a Three-way Alignment*. Tristan Miller and Iryna Gurevych. 2014 [https://pdfs.semanticscholar.org/90cd/22a9cd59dc1fc21f4ec36e9c7d95085f7fb6.pdf](https://pdfs.semanticscholar.org/90cd/22a9cd59dc1fc21f4ec36e9c7d95085f7fb6.pdf)\n\n\n",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "",
        "keywords": "Word Sense Disambiguation,NLP",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "wrapperWSD",
        "package_url": "https://pypi.org/project/wrapperWSD/",
        "platform": "",
        "project_url": "https://pypi.org/project/wrapperWSD/",
        "project_urls": null,
        "release_url": "https://pypi.org/project/wrapperWSD/0.0.3/",
        "requires_dist": [
            "check-manifest ; extra == 'dev'",
            "coverage ; extra == 'test'"
        ],
        "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
        "summary": "Word Sense Disambiguation wrapper",
        "version": "0.0.3"
    },
    "last_serial": 6001783,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "5f808ae324cd6181581b4bfa72fafa39",
                    "sha256": "583eb554f19ed2da1224ad5dea93010e3246af95a86df9f7ed90ea7c56deda96"
                },
                "downloads": -1,
                "filename": "wrapperWSD-0.0.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "5f808ae324cd6181581b4bfa72fafa39",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
                "size": 2608,
                "upload_time": "2019-10-19T03:40:37",
                "url": "https://files.pythonhosted.org/packages/1c/fb/aebac468f558b75bd4731aaf8ed520b913e3ca940aeb30a918e65193b6e2/wrapperWSD-0.0.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "a53c472f177cd2496ecfb5a0e1c8fbb2",
                    "sha256": "c7135616ed20793168cb806fb559ce45ea4e246af50a26cfca064431eb7848ab"
                },
                "downloads": -1,
                "filename": "wrapperWSD-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "a53c472f177cd2496ecfb5a0e1c8fbb2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
                "size": 5778,
                "upload_time": "2019-10-19T03:40:40",
                "url": "https://files.pythonhosted.org/packages/9e/58/f3c7381451b292cbe60a4a8a5c47d650e59ab6c6e71ebdba0f5a6c1d9db9/wrapperWSD-0.0.1.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "32c40491e3cada046679ed538a8be4b3",
                    "sha256": "2be82c710270bd7f3d3bf1ea40f1121bc2f70f4d893b49311e22b804fc91a803"
                },
                "downloads": -1,
                "filename": "wrapperWSD-0.0.2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "32c40491e3cada046679ed538a8be4b3",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
                "size": 479050,
                "upload_time": "2019-10-19T03:51:12",
                "url": "https://files.pythonhosted.org/packages/3c/d4/e8cef683200d0bf6a21bf6d76cccfe4e70bd00a05a37e74caa9047e9e4a6/wrapperWSD-0.0.2-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "8630313b0515efb07a08b6f7b3066778",
                    "sha256": "fca180a1c7535a427323424cf80ffbaedebfc2344390f0771170dc27ab4266a1"
                },
                "downloads": -1,
                "filename": "wrapperWSD-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "8630313b0515efb07a08b6f7b3066778",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
                "size": 473661,
                "upload_time": "2019-10-19T03:51:15",
                "url": "https://files.pythonhosted.org/packages/55/3a/7aa99660eba7da760e3c5f5c17a2d064fa09fa9f67f2480ce52cfd2d677c/wrapperWSD-0.0.2.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "df0d5f33f3a33dbf7fdfa1db0d48ab0c",
                    "sha256": "041bc2afd15f13b7ac923245e4ec2964a6995de15682b744d3deb4488e1de978"
                },
                "downloads": -1,
                "filename": "wrapperWSD-0.0.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "df0d5f33f3a33dbf7fdfa1db0d48ab0c",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
                "size": 479575,
                "upload_time": "2019-10-20T03:25:42",
                "url": "https://files.pythonhosted.org/packages/97/6c/11106949bc596518f3d5970e1475565c8643dcde1427d1b593fe30260b52/wrapperWSD-0.0.3-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "ab6ffb9ec2d6dd89cf7d2fd36fc212eb",
                    "sha256": "1b3af7f83aa1f93916fed722a10476880e6c220deae270f6f9e1bacab3bc5a0b"
                },
                "downloads": -1,
                "filename": "wrapperWSD-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "ab6ffb9ec2d6dd89cf7d2fd36fc212eb",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
                "size": 474820,
                "upload_time": "2019-10-20T03:25:46",
                "url": "https://files.pythonhosted.org/packages/a5/07/90f1926d78a4ac5740b726bcaf6e931adfbbc45167db4301d11ced0b5158/wrapperWSD-0.0.3.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "df0d5f33f3a33dbf7fdfa1db0d48ab0c",
                "sha256": "041bc2afd15f13b7ac923245e4ec2964a6995de15682b744d3deb4488e1de978"
            },
            "downloads": -1,
            "filename": "wrapperWSD-0.0.3-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "df0d5f33f3a33dbf7fdfa1db0d48ab0c",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
            "size": 479575,
            "upload_time": "2019-10-20T03:25:42",
            "url": "https://files.pythonhosted.org/packages/97/6c/11106949bc596518f3d5970e1475565c8643dcde1427d1b593fe30260b52/wrapperWSD-0.0.3-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "ab6ffb9ec2d6dd89cf7d2fd36fc212eb",
                "sha256": "1b3af7f83aa1f93916fed722a10476880e6c220deae270f6f9e1bacab3bc5a0b"
            },
            "downloads": -1,
            "filename": "wrapperWSD-0.0.3.tar.gz",
            "has_sig": false,
            "md5_digest": "ab6ffb9ec2d6dd89cf7d2fd36fc212eb",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4",
            "size": 474820,
            "upload_time": "2019-10-20T03:25:46",
            "url": "https://files.pythonhosted.org/packages/a5/07/90f1926d78a4ac5740b726bcaf6e931adfbbc45167db4301d11ced0b5158/wrapperWSD-0.0.3.tar.gz"
        }
    ]
}