Created
March 5, 2020 14:36
-
-
Save fnielsen/499d1faaf8601e21e9ff54d0212e565e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Homographs - wordnet\n", | |
"====================" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"from os.path import expanduser, join\n", | |
"from rdflib import Graph\n", | |
"from nltk.corpus import wordnet as wn" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"dannet_path = expanduser(join('~', 'data', 'dannet', 'DanNet-2.2_owl'))\n", | |
"words_filename = join(dannet_path, 'words.rdf')\n", | |
"wordsenses_filename = join(dannet_path, 'wordsenses.rdf')\n", | |
"glossary_filename = join(dannet_path, 'glossary.rdf')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"<Graph identifier=N6f37c91961f6412ba1ad6facec1afa73 (<class 'rdflib.graph.Graph'>)>" | |
] | |
}, | |
"execution_count": 3, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"g = Graph()\n", | |
"g.parse(words_filename)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"<Graph identifier=N6f37c91961f6412ba1ad6facec1afa73 (<class 'rdflib.graph.Graph'>)>" | |
] | |
}, | |
"execution_count": 4, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"g.parse(wordsenses_filename)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"<Graph identifier=N6f37c91961f6412ba1ad6facec1afa73 (<class 'rdflib.graph.Graph'>)>" | |
] | |
}, | |
"execution_count": 5, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"g.parse(glossary_filename)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"query = \"\"\"\n", | |
"PREFIX wn20schema: <http://www.w3.org/2006/03/wn/wn20/schema/>\n", | |
"\n", | |
"SELECT ?synset ?wordsense ?word ?gloss {\n", | |
" ?word wn20schema:lexicalForm \"bil\" .\n", | |
" ?wordsense wn20schema:word ?word .\n", | |
" ?synset wn20schema:containsWordSense ?wordsense . \n", | |
" ?synset wn20schema:gloss ?gloss .\n", | |
"}\n", | |
"\"\"\"" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"query_results = g.query(query)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"-\n", | |
"firehjulet motorkøretøj til person- el. godstransp ... (Brug: \"min bil gik i stå, fordi der ikke var mere benzin i den || du har overhovedet ikke herredømme over bilen, når du enten har sat bilen i frigear eller har koblet ud\")\n" | |
] | |
} | |
], | |
"source": [ | |
"for row in query_results:\n", | |
" print(\"-\")\n", | |
" print(row[3])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"synsets = wn.synsets(\"station\")" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"-\n", | |
"a facility equipped with special equipment and personnel for a particular purpose\n", | |
"-\n", | |
"proper or designated social situation\n", | |
"-\n", | |
"(nautical) the location to which a ship or fleet is assigned for duty\n", | |
"-\n", | |
"the position where someone (as a guard or sentry) stands or is assigned to stand\n", | |
"-\n", | |
"the frequency assigned to a broadcasting station\n", | |
"-\n", | |
"assign to a station\n" | |
] | |
} | |
], | |
"source": [ | |
"for synset in synsets:\n", | |
" print('-')\n", | |
" print(synset.definition())" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.9" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment