Merge branch 'master' of ssh://the-cake-is-a-lie.net:20022/jonas/NLP-LAB
This commit is contained in:
commit
138d5e6f3d
@ -205,24 +205,14 @@
|
|||||||
"cell_type": "markdown",
|
"cell_type": "markdown",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"## Exercises:"
|
"## Task 01:"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "markdown",
|
"cell_type": "markdown",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"### Exercise 01\n"
|
"### Performance 1\n"
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 10,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"accs = [0] * 5\n",
|
|
||||||
"names = [\"M1\", \"M2\", \"M3\", \"M4\", \"M5\"]\n"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -235,28 +225,15 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 9,
|
"execution_count": 16,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [
|
"outputs": [],
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"start training…\n",
|
|
||||||
"training done\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
"source": [
|
||||||
"annotated_sent = nltk.corpus.treebank.tagged_sents()\n",
|
"def model_01(X,y,tX,ty, max_size=1000):\n",
|
||||||
"\n",
|
|
||||||
"X,y,tX,ty = create_training_and_test_set(annotated_sentences=annotated_sent, \n",
|
|
||||||
" relative_cutoff=0.8)\n",
|
|
||||||
"\n",
|
|
||||||
" #classifier = DecisionTreeClassifier(criterion='entropy')\n",
|
" #classifier = DecisionTreeClassifier(criterion='entropy')\n",
|
||||||
" from sklearn.neural_network import MLPClassifier\n",
|
" from sklearn.neural_network import MLPClassifier\n",
|
||||||
"model01_clf = train_classifier(X,y,MLPClassifier(),max_size=10000)\n",
|
" model01_clf = train_classifier(X,y,MLPClassifier(),max_size=max_size)\n",
|
||||||
"accs[0] = test_classifier(clf=clf, tX=tX, ty=ty)"
|
" return test_classifier(clf=model01_clf, tX=tX, ty=ty)"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -266,79 +243,291 @@
|
|||||||
"#### Model 02"
|
"#### Model 02"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 13,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"data": {
|
|
||||||
"text/plain": [
|
|
||||||
"0"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
"execution_count": 13,
|
|
||||||
"metadata": {},
|
|
||||||
"output_type": "execute_result"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"accs[1]"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 8,
|
"execution_count": 8,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [
|
"outputs": [],
|
||||||
{
|
|
||||||
"data": {
|
|
||||||
"text/plain": [
|
|
||||||
"'\\nimport matplotlib.pyplot as plt\\nimport numpy as np\\n\\nweights = clf.named_steps[\\'classifier\\'].feature_importances_\\nlabels = clf.named_steps[\\'vectorizer\\'].get_feature_names()\\n\\n#sort\\nweights, labels = (list(t) for t in zip(*sorted(zip(weights, labels))))\\n\\n#fig_1, ax_1 = plt.subplots()\\n#plt.bar(np.arange(len(weights)), weights)\\n#plt.xticks(np.arange(len(weights)), labels, rotation=90)\\n#plt.show()\\n\\nprint(\"Most important features:\")\\npprint.pprint(list(reversed(labels[-20:])))\\nprint(\"with weights: \")\\npprint.pprint(list(reversed(weights[-20:])))\\n'"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
"execution_count": 8,
|
|
||||||
"metadata": {},
|
|
||||||
"output_type": "execute_result"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
"source": [
|
||||||
"'''\n",
|
"def model_02(tX,ty):\n",
|
||||||
"import matplotlib.pyplot as plt\n",
|
" m2_y = nltk.pos_tag([w['word'] for w in tX])\n",
|
||||||
"import numpy as np\n",
|
" # compare results\n",
|
||||||
"\n",
|
" n_correct = sum((1 if m2_y[i][1] == ty[i] else 0) for i in range(len(ty)))\n",
|
||||||
"weights = clf.named_steps['classifier'].feature_importances_\n",
|
" return n_correct / len(ty)"
|
||||||
"labels = clf.named_steps['vectorizer'].get_feature_names()\n",
|
|
||||||
"\n",
|
|
||||||
"#sort\n",
|
|
||||||
"weights, labels = (list(t) for t in zip(*sorted(zip(weights, labels))))\n",
|
|
||||||
"\n",
|
|
||||||
"#fig_1, ax_1 = plt.subplots()\n",
|
|
||||||
"#plt.bar(np.arange(len(weights)), weights)\n",
|
|
||||||
"#plt.xticks(np.arange(len(weights)), labels, rotation=90)\n",
|
|
||||||
"#plt.show()\n",
|
|
||||||
"\n",
|
|
||||||
"print(\"Most important features:\")\n",
|
|
||||||
"pprint.pprint(list(reversed(labels[-20:])))\n",
|
|
||||||
"print(\"with weights: \")\n",
|
|
||||||
"pprint.pprint(list(reversed(weights[-20:])))\n",
|
|
||||||
"'''"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "markdown",
|
"cell_type": "markdown",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"```\n",
|
"#### Model 03"
|
||||||
"from sklearn import tree\n",
|
]
|
||||||
"import graphviz\n",
|
},
|
||||||
"dot_data = tree.export_graphviz(clf.named_steps['classifier'], out_file='test',\n",
|
{
|
||||||
" feature_names=labels,\n",
|
"cell_type": "code",
|
||||||
" filled=True, rounded=True, \n",
|
"execution_count": 9,
|
||||||
" special_characters=True)\n",
|
"metadata": {},
|
||||||
"#graph = graphviz.Source(dot_data)\n",
|
"outputs": [],
|
||||||
"#graph\n",
|
"source": [
|
||||||
"```"
|
"def model_03(corpus_tagged, corpus_sents, cut=0.8):\n",
|
||||||
|
" \n",
|
||||||
|
" patterns = [(r'.*ing$', 'VBG'), (r'.*ed$', 'VBD'), (r'.*es$', 'VBZ'), (r'.*ould$', 'MD'), (r'.*\\'s$', 'NN$'), \n",
|
||||||
|
" (r'.*s$', 'NNS'), (r'^-?[0-9]+(.[0-9]+)?$', 'CD'), (r'.*', 'NN')]\n",
|
||||||
|
" \n",
|
||||||
|
" s = int(len(corpus_tagged) * cut)\n",
|
||||||
|
" train_sents = corpus_tagged[:s]\n",
|
||||||
|
" test_sents = corpus_tagged[s:]\n",
|
||||||
|
" \n",
|
||||||
|
" models = {\n",
|
||||||
|
" 'def_model': nltk.DefaultTagger('NN'),\n",
|
||||||
|
" 'regexp_model': nltk.RegexpTagger(patterns),\n",
|
||||||
|
" 'uni_model': nltk.UnigramTagger(train_sents),\n",
|
||||||
|
" 'bi_model': nltk.BigramTagger(train_sents),\n",
|
||||||
|
" 'tri_model': nltk.TrigramTagger(train_sents)\n",
|
||||||
|
" }\n",
|
||||||
|
" \n",
|
||||||
|
" performance = {}\n",
|
||||||
|
" for name,model in models.items():\n",
|
||||||
|
" performance[name] = model.evaluate(test_sents)\n",
|
||||||
|
" \n",
|
||||||
|
" return performance\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### Applying models on Datasets"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"[('Pierre', 'NNP'),\n",
|
||||||
|
" ('Vinken', 'NNP'),\n",
|
||||||
|
" (',', ','),\n",
|
||||||
|
" ('61', 'CD'),\n",
|
||||||
|
" ('years', 'NNS'),\n",
|
||||||
|
" ('old', 'JJ'),\n",
|
||||||
|
" (',', ','),\n",
|
||||||
|
" ('will', 'MD'),\n",
|
||||||
|
" ('join', 'VB'),\n",
|
||||||
|
" ('the', 'DT'),\n",
|
||||||
|
" ('board', 'NN'),\n",
|
||||||
|
" ('as', 'IN'),\n",
|
||||||
|
" ('a', 'DT'),\n",
|
||||||
|
" ('nonexecutive', 'JJ'),\n",
|
||||||
|
" ('director', 'NN'),\n",
|
||||||
|
" ('Nov.', 'NNP'),\n",
|
||||||
|
" ('29', 'CD'),\n",
|
||||||
|
" ('.', '.')]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"P1.1\n",
|
||||||
|
"start training…\n",
|
||||||
|
"training done\n",
|
||||||
|
"Accuracy: 0.7671041469135187\n",
|
||||||
|
"P1.2\n",
|
||||||
|
"P1.3\n",
|
||||||
|
"P1.4\n",
|
||||||
|
"start training…\n",
|
||||||
|
"training done\n",
|
||||||
|
"Accuracy: 0.6359655404139998\n",
|
||||||
|
"P1.5\n",
|
||||||
|
"P1.6\n",
|
||||||
|
"{'P1.1': 0.7671041469135187,\n",
|
||||||
|
" 'P1.2': 0.8936074654423873,\n",
|
||||||
|
" 'P1.3 -- bi_model': 0.1132791057437996,\n",
|
||||||
|
" 'P1.3 -- def_model': 0.1447677029791906,\n",
|
||||||
|
" 'P1.3 -- regexp_model': 0.24232746145017217,\n",
|
||||||
|
" 'P1.3 -- tri_model': 0.06736863116922003,\n",
|
||||||
|
" 'P1.3 -- uni_model': 0.8608213982733669,\n",
|
||||||
|
" 'P1.4': 0.6359655404139998,\n",
|
||||||
|
" 'P1.5': 0.6044583741861567,\n",
|
||||||
|
" 'P1.6 -- bi_model': 0.1132791057437996,\n",
|
||||||
|
" 'P1.6 -- def_model': 0.1447677029791906,\n",
|
||||||
|
" 'P1.6 -- regexp_model': 0.24232746145017217,\n",
|
||||||
|
" 'P1.6 -- tri_model': 0.06736863116922003,\n",
|
||||||
|
" 'P1.6 -- uni_model': 0.8608213982733669}\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"performances = {}\n",
|
||||||
|
"\n",
|
||||||
|
"treebank_tagged = nltk.corpus.treebank.tagged_sents()\n",
|
||||||
|
"treebank_sents = nltk.corpus.treebank.sents()\n",
|
||||||
|
"\n",
|
||||||
|
"brown_tagged = nltk.corpus.brown.tagged_sents()#(categories='news')\n",
|
||||||
|
"brown_sents = nltk.corpus.brown.sents()#(categories='news')\n",
|
||||||
|
"\n",
|
||||||
|
"display(treebank_tagged[0])\n",
|
||||||
|
"\n",
|
||||||
|
"X1,y1,tX1,ty1 = create_training_and_test_set(annotated_sentences=treebank_tagged, \n",
|
||||||
|
" relative_cutoff=0.8)\n",
|
||||||
|
"\n",
|
||||||
|
"X2,y2,tX2,ty2 = create_training_and_test_set(annotated_sentences=brown_tagged, \n",
|
||||||
|
" relative_cutoff=0.8)\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"P1.1\")\n",
|
||||||
|
"performances['P1.1'] = model_01(X1,y1,tX1,ty1)\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"P1.2\")\n",
|
||||||
|
"performances['P1.2'] = model_02(tX1,ty1)\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"P1.3\")\n",
|
||||||
|
"p3 = model_03(treebank_tagged, treebank_sents)\n",
|
||||||
|
"for k,v in p3.items():\n",
|
||||||
|
" performances[\"P1.3 -- \" + k] = v\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"P1.4\")\n",
|
||||||
|
"performances['P1.4'] = model_01(X2,y2,tX2,ty2)\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"P1.5\")\n",
|
||||||
|
"performances['P1.5'] = model_02(tX2,ty2)\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"P1.6\")\n",
|
||||||
|
"p6 = model_03(brown_tagged, brown_sents)\n",
|
||||||
|
"for k,v in p3.items():\n",
|
||||||
|
" performances[\"P1.6 -- \" + k] = v\n",
|
||||||
|
"\n",
|
||||||
|
"pprint.pprint(performances)\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### Plotting Data"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"application/vnd.jupyter.widget-view+json": {
|
||||||
|
"model_id": "c148aec5450948cea1f32c302344dbab",
|
||||||
|
"version_major": 2,
|
||||||
|
"version_minor": 0
|
||||||
|
},
|
||||||
|
"text/html": [
|
||||||
|
"<p>Failed to display Jupyter Widget of type <code>FigureCanvasNbAgg</code>.</p>\n",
|
||||||
|
"<p>\n",
|
||||||
|
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
|
||||||
|
" that the widgets JavaScript is still loading. If this message persists, it\n",
|
||||||
|
" likely means that the widgets JavaScript library is either not installed or\n",
|
||||||
|
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
|
||||||
|
" Widgets Documentation</a> for setup instructions.\n",
|
||||||
|
"</p>\n",
|
||||||
|
"<p>\n",
|
||||||
|
" If you're reading this message in another frontend (for example, a static\n",
|
||||||
|
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
|
||||||
|
" it may mean that your frontend doesn't currently support widgets.\n",
|
||||||
|
"</p>\n"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
"FigureCanvasNbAgg()"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"import matplotlib.pyplot as plt\n",
|
||||||
|
"import numpy as np\n",
|
||||||
|
"#weights = clf.named_steps['classifier'].feature_importances_\n",
|
||||||
|
"#labels = clf.named_steps['vectorizer'].get_feature_names()\n",
|
||||||
|
"\n",
|
||||||
|
"#sort\n",
|
||||||
|
"#weights, labels = (list(t) for t in zip(*sorted(zip(weights, labels))))\n",
|
||||||
|
"\n",
|
||||||
|
"fig_1, ax_1 = plt.subplots()\n",
|
||||||
|
"plt.bar(np.arange(len(performances)), performances.values())\n",
|
||||||
|
"plt.xticks(np.arange(len(performances)), performances.keys(), rotation=30, ha='right')\n",
|
||||||
|
"plt.tight_layout()\n",
|
||||||
|
"plt.show()\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"----\n",
|
||||||
|
"## Task 2"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"WORDS = 'words' #: column type for words\n",
|
||||||
|
"POS = 'pos' #: column type for part-of-speech tags\n",
|
||||||
|
"TREE = 'tree' #: column type for parse trees\n",
|
||||||
|
"CHUNK = 'chunk' #: column type for chunk structures\n",
|
||||||
|
"NE = 'ne' #: column type for named entities\n",
|
||||||
|
"SRL = 'srl' #: column type for semantic role labels\n",
|
||||||
|
"IGNORE = 'ignore' #: column type for column that should be ignored\n",
|
||||||
|
"train_path = \"./ru_syntagrus-ud-train.conllu\"\n",
|
||||||
|
"ru_corp = nltk.corpus.ConllCorpusReader(root=\"./\", \n",
|
||||||
|
" fileids=[\"ru_syntagrus-ud-train-uncommented.conllu\"],\n",
|
||||||
|
" columntypes=[IGNORE, WORDS, IGNORE, POS],\n",
|
||||||
|
" encoding='utf-8')\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 13,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"ru_tagged = ru_corp.tagged_sents()\n",
|
||||||
|
"\n",
|
||||||
|
"ru_tagged[0]\n",
|
||||||
|
"\n",
|
||||||
|
"X3,y3,tX3,ty3 = create_training_and_test_set(annotated_sentences=ru_tagged, \n",
|
||||||
|
" relative_cutoff=0.8)\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 18,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"P2.1\n",
|
||||||
|
"start training…\n",
|
||||||
|
"training done\n",
|
||||||
|
"Accuracy: 0.7043834741655548\n",
|
||||||
|
"0.7043834741655548\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"print(\"P2.1\")\n",
|
||||||
|
"performances['P2.1'] = model_01(X3,y3,tX3,ty3, max_size=1000)\n",
|
||||||
|
"print(performances['P2.1'])"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -365,7 +554,7 @@
|
|||||||
"name": "python",
|
"name": "python",
|
||||||
"nbconvert_exporter": "python",
|
"nbconvert_exporter": "python",
|
||||||
"pygments_lexer": "ipython3",
|
"pygments_lexer": "ipython3",
|
||||||
"version": "3.6.3"
|
"version": "3.6.5"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"nbformat": 4,
|
"nbformat": 4,
|
||||||
|
26356
Jonas_Solutions/ru-upos.DICT
Normal file
26356
Jonas_Solutions/ru-upos.DICT
Normal file
File diff suppressed because it is too large
Load Diff
382
Jonas_Solutions/ru-upos.RDR
Normal file
382
Jonas_Solutions/ru-upos.RDR
Normal file
@ -0,0 +1,382 @@
|
|||||||
|
True : object.conclusion = "NN"
|
||||||
|
object.tag == "ADV" : object.conclusion = "ADV"
|
||||||
|
object.suffixL3 == "ено" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "ано" : object.conclusion = "VERB"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.nextTag1 == "PUNCT" and object.nextTag2 == "NOUN" : object.conclusion = "NOUN"
|
||||||
|
object.word == "так" and object.nextWord1 == "как" : object.conclusion = "SCONJ"
|
||||||
|
object.suffixL3 == "ино" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.suffixL3 == "нко" : object.conclusion = "PROPN"
|
||||||
|
object.word == "всё" and object.nextTag1 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.nextTag1 == "SYM" : object.conclusion = "NUM"
|
||||||
|
object.suffixL3 == "бро" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ако" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "йко" : object.conclusion = "PROPN"
|
||||||
|
object.word == "Сити" and object.nextWord1 == "''" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "бюро" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord1 == "км" : object.conclusion = "NUM"
|
||||||
|
object.nextWord1 == "года" : object.conclusion = "ADJ"
|
||||||
|
object.tag == "NOUN" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "ском" : object.conclusion = "ADJ"
|
||||||
|
object.word == "войском" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "кие" : object.conclusion = "ADJ"
|
||||||
|
object.prevTag1 == "PUNCT" and object.word == "русские" and object.nextTag1 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ыми" : object.conclusion = "ADJ"
|
||||||
|
object.prevTag1 == "PUNCT" and object.nextTag1 == "ADP" : object.conclusion = "VERB"
|
||||||
|
object.prevTag1 == "PROPN" and object.nextTag1 == "PUNCT" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL2 == "es" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "" : object.conclusion = "ADV"
|
||||||
|
object.suffixL2 == "ми" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL2 == "ия" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.word == "Entertainment" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL2 == "ns" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ing" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord2 == ":" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.nextTag1 == "PUNCT" and object.nextTag2 == "NUM" : object.conclusion = "NOUN"
|
||||||
|
object.nextTag1 == "PUNCT" and object.nextTag2 == "ADP" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag2 == "VERB" and object.prevTag1 == "NOUN" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "ена" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ими" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "," : object.conclusion = "VERB"
|
||||||
|
object.word == "русскими" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "ьном" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL3 == "шие" : object.conclusion = "VERB"
|
||||||
|
object.prevWord1 == "" : object.conclusion = "ADJ"
|
||||||
|
object.nextTag1 == "NOUN" and object.nextTag2 == "NOUN" : object.conclusion = "AUX"
|
||||||
|
object.suffixL3 == "ово" : object.conclusion = "PROPN"
|
||||||
|
object.word == "слово" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ова" : object.conclusion = "PROPN"
|
||||||
|
object.word == "слова" : object.conclusion = "NOUN"
|
||||||
|
object.word == "острова" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "ADJ" and object.nextTag1 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "DET" and object.word == "вдова" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "ющей" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "щие" : object.conclusion = "VERB"
|
||||||
|
object.nextWord1 == "," : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "PROPN" and object.nextTag1 == "VERB" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord2 == "альбом" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord2 == "-" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "PUNCT" and object.word == "м" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "нном" : object.conclusion = "ADJ"
|
||||||
|
object.prevTag1 == "PUNCT" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "рном" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "тном" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "городе" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "ева" : object.conclusion = "PROPN"
|
||||||
|
object.word == "королева" and object.nextTag1 == "NOUN" and object.nextTag2 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ево" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "ески" : object.conclusion = "ADV"
|
||||||
|
object.prevTag1 == "ADV" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "город" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "овом" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "чном" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "реки" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "эля" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "вшей" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "дние" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "дном" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "арда" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "тоне" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "рге" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "города" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "йти" : object.conclusion = "VERB"
|
||||||
|
object.prevWord1 == "*" : object.conclusion = "ADV"
|
||||||
|
object.suffixL3 == "кии" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "поле" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "овка" : object.conclusion = "PROPN"
|
||||||
|
object.nextTag1 == "NOUN" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "провинцию" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "ичем" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord2 == "родился" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "ёва" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "поль" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "деревня" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "алия" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "льда" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "ите" : object.conclusion = "VERB"
|
||||||
|
object.prevTag1 == "ADP" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "бном" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL3 == "ида" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "ндия" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "тове" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "асом" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "нчи" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "бии" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "эль" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "мми" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "евка" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "кию" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "нне" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "у" and object.nextWord1 == ";" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "тти" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "кера" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "кове" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "село" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "рант" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "ндию" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "ейма" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "в" and object.nextWord1 == "(" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag2 == "ADJ" and object.prevTag1 == "ADP" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "Южной" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "святого" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord1 == "родился" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "берт" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "дора" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "нята" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "тней" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "жном" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "мном" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "сном" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "-" and object.word == "мм" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "нней" : object.conclusion = "ADJ"
|
||||||
|
object.tag == "NUM" : object.conclusion = "NUM"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.suffixL4 == "BASE" : object.conclusion = "PROPN"
|
||||||
|
object.nextTag1 == "NOUN" and object.nextTag2 == "ADJ" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL2 == "их" : object.conclusion = "NUM"
|
||||||
|
object.prevTag2 == "ADP" and object.prevTag1 == "PRON" : object.conclusion = "NUM"
|
||||||
|
object.prevWord1 == "," : object.conclusion = "NUM"
|
||||||
|
object.suffixL4 == "ному" : object.conclusion = "NUM"
|
||||||
|
object.prevWord2 == "на" : object.conclusion = "NUM"
|
||||||
|
object.prevTag1 == "DET" : object.conclusion = "NUM"
|
||||||
|
object.prevWord1 == "площадью" : object.conclusion = "NUM"
|
||||||
|
object.nextWord1 == "году" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.prevWord2 == "Ямал" : object.conclusion = "NUM"
|
||||||
|
object.prevWord1 == "-" and object.word == "ти" : object.conclusion = "NUM"
|
||||||
|
object.prevTag1 == "PUNCT" and object.word == "1" and object.nextTag1 == "PUNCT" : object.conclusion = "NUM"
|
||||||
|
object.nextWord1 == "года" : object.conclusion = "ADJ"
|
||||||
|
object.word == "два" : object.conclusion = "NUM"
|
||||||
|
object.word == "три" and object.nextWord1 == "года" : object.conclusion = "NUM"
|
||||||
|
object.prevWord2 == "," : object.conclusion = "NUM"
|
||||||
|
object.prevWord1 == "на" : object.conclusion = "NUM"
|
||||||
|
object.prevTag1 == "ADP" and object.word == "2" and object.nextTag1 == "NOUN" : object.conclusion = "NUM"
|
||||||
|
object.word == "3" : object.conclusion = "NUM"
|
||||||
|
object.nextWord1 == "годах" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "г." : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "С" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "января" : object.conclusion = "ADJ"
|
||||||
|
object.word == "много" and object.nextTag1 == "VERB" : object.conclusion = "ADV"
|
||||||
|
object.nextWord1 == "годов" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "г" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "июня" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "сентября" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "октября" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "августа" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL2 == "S2" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord1 == "гг" : object.conclusion = "ADJ"
|
||||||
|
object.nextTag1 == "PRON" and object.nextTag2 == "VERB" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "В" and object.nextWord1 == "--" : object.conclusion = "ADJ"
|
||||||
|
object.nextWord1 == "ноября" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "в" and object.nextWord1 == "--" : object.conclusion = "ADJ"
|
||||||
|
object.tag == "ADP" : object.conclusion = "ADP"
|
||||||
|
object.prevWord1 == "так" and object.word == "как" : object.conclusion = "ADV"
|
||||||
|
object.prevTag1 == "ADJ" and object.word == "типа" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "NOUN" and object.word == "как" and object.nextTag1 == "ADP" : object.conclusion = "ADV"
|
||||||
|
object.word == "Как" and object.nextTag1 == "VERB" : object.conclusion = "SCONJ"
|
||||||
|
object.word == "как" and object.nextTag1 == "VERB" and object.nextTag2 == "ADP" : object.conclusion = "ADV"
|
||||||
|
object.prevWord2 == "того" and object.prevWord1 == "," and object.word == "как" : object.conclusion = "SCONJ"
|
||||||
|
object.prevWord1 == "того" and object.word == "как" : object.conclusion = "SCONJ"
|
||||||
|
object.tag == "PRON" : object.conclusion = "PRON"
|
||||||
|
object.word == "том" and object.nextTag1 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.nextTag1 == "PART" and object.nextTag2 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.nextWord1 == "просто" : object.conclusion = "PRON"
|
||||||
|
object.prevWord1 == "--" and object.word == "это" : object.conclusion = "AUX"
|
||||||
|
object.word == "это" and object.nextTag1 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.prevTag1 == "" and object.nextTag1 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.word == "т." and object.nextTag1 == "ADV" : object.conclusion = "ADV"
|
||||||
|
object.prevWord1 == "в" and object.word == "этом" : object.conclusion = "DET"
|
||||||
|
object.word == "всего" and object.nextTag1 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.word == "того" and object.nextWord1 == "времени" : object.conclusion = "DET"
|
||||||
|
object.tag == "SCONJ" : object.conclusion = "SCONJ"
|
||||||
|
object.word == "что" and object.nextTag1 == "VERB" : object.conclusion = "PRON"
|
||||||
|
object.prevWord2 == "том" and object.word == "что" : object.conclusion = "SCONJ"
|
||||||
|
object.prevWord2 == "признал" and object.word == "что" : object.conclusion = "SCONJ"
|
||||||
|
object.nextWord2 == "в" : object.conclusion = "SCONJ"
|
||||||
|
object.word == "потому" and object.nextTag1 == "PUNCT" : object.conclusion = "ADV"
|
||||||
|
object.tag == "PROPN" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag1 == "AUX" : object.conclusion = "VERB"
|
||||||
|
object.suffixL2 == "ий" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "" : object.conclusion = "PROPN"
|
||||||
|
object.nextTag1 == "PROPN" and object.nextTag2 == "PUNCT" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "-" and object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.suffixL4 == "ован" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "мена" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "гион" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord1 == "of" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag2 == "VERB" and object.prevTag1 == "ADJ" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag1 == "NUM" and object.nextTag1 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "овед" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag2 == "ADJ" and object.prevTag1 == "ADJ" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "ога" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "чена" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "вана" : object.conclusion = "VERB"
|
||||||
|
object.word == "Ивана" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "нена" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "чна" : object.conclusion = "ADJ"
|
||||||
|
object.nextTag1 == "PRON" and object.nextTag2 == "VERB" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ics" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "VERB" and object.nextTag1 == "ADP" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord2 == "" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL2 == "ua" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ача" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL2 == "nd" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "sis" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "of" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "ADP" and object.nextTag1 == "PROPN" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL2 == "ry" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord1 == "the" : object.conclusion = "VERB"
|
||||||
|
object.suffixL2 == "ed" : object.conclusion = "VERB"
|
||||||
|
object.prevTag2 == "PUNCT" and object.prevTag1 == "NOUN" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord1 == "Airlines" : object.conclusion = "ADJ"
|
||||||
|
object.tag == "DET" : object.conclusion = "DET"
|
||||||
|
object.nextWord2 == "что" : object.conclusion = "PRON"
|
||||||
|
object.word == "его" and object.nextTag1 == "VERB" : object.conclusion = "PRON"
|
||||||
|
object.prevTag1 == "PUNCT" and object.word == "то" : object.conclusion = "ADV"
|
||||||
|
object.word == "то" and object.nextWord1 == "есть" : object.conclusion = "PRON"
|
||||||
|
object.nextWord1 == "с" : object.conclusion = "CCONJ"
|
||||||
|
object.prevTag1 == "VERB" and object.nextTag1 == "ADP" : object.conclusion = "PRON"
|
||||||
|
object.nextWord1 == "из" : object.conclusion = "DET"
|
||||||
|
object.prevTag1 == "ADP" and object.word == "этого" : object.conclusion = "PRON"
|
||||||
|
object.nextTag2 == "PUNCT" : object.conclusion = "DET"
|
||||||
|
object.nextTag1 == "NOUN" and object.nextTag2 == "NOUN" : object.conclusion = "DET"
|
||||||
|
object.word == "этого" and object.nextTag1 == "NOUN" and object.nextTag2 == "ADP" : object.conclusion = "DET"
|
||||||
|
object.nextTag2 == "PRON" : object.conclusion = "DET"
|
||||||
|
object.prevWord1 == "с" : object.conclusion = "DET"
|
||||||
|
object.prevTag1 == "VERB" and object.nextTag1 == "ADV" : object.conclusion = "PRON"
|
||||||
|
object.prevTag1 == "ADJ" and object.nextTag1 == "ADP" : object.conclusion = "PRON"
|
||||||
|
object.prevTag1 == "NOUN" and object.nextTag1 == "ADP" : object.conclusion = "PRON"
|
||||||
|
object.prevTag1 == "VERB" and object.word == "его" and object.nextTag1 == "PUNCT" : object.conclusion = "PRON"
|
||||||
|
object.nextTag1 == "CCONJ" : object.conclusion = "PRON"
|
||||||
|
object.prevTag2 == "PRON" and object.prevTag1 == "VERB" and object.word == "её" : object.conclusion = "PRON"
|
||||||
|
object.nextTag1 == "PUNCT" and object.nextTag2 == "NOUN" : object.conclusion = "PRON"
|
||||||
|
object.word == "его" and object.nextTag1 == "PUNCT" : object.conclusion = "DET"
|
||||||
|
object.tag == "SYM" : object.conclusion = "SYM"
|
||||||
|
object.tag == "PART" : object.conclusion = "PART"
|
||||||
|
object.tag == "PUNCT" : object.conclusion = "PUNCT"
|
||||||
|
object.tag == "VERB" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "ость" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "ADJ" and object.nextTag1 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.nextTag2 == "SCONJ" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "тели" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "NOUN" and object.word == "хотели" and object.nextTag1 == "VERB" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "лла" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "ины" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "щины" : object.conclusion = "PROPN"
|
||||||
|
object.nextTag2 == "" : object.conclusion = "PROPN"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.suffixL3 == "лав" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord1 == "-" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "оны" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "``" and object.nextWord1 == "''" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL2 == "ен" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag2 == "CCONJ" and object.prevTag1 == "PUNCT" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "вен" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL3 == "мен" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "лли" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL4 == "итет" : object.conclusion = "NOUN"
|
||||||
|
object.prevTag1 == "NOUN" and object.word == "правил" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "мены" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "иала" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "кет" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord1 == "города" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "уны" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "пись" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "дли" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag2 == "NOUN" and object.prevTag1 == "ADP" : object.conclusion = "PROPN"
|
||||||
|
object.nextTag1 == "PUNCT" and object.nextTag2 == "PROPN" : object.conclusion = "PROPN"
|
||||||
|
object.suffixL2 == "ся" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "льны" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL3 == "тен" : object.conclusion = "ADJ"
|
||||||
|
object.tag == "X" : object.conclusion = "X"
|
||||||
|
object.tag == "CCONJ" : object.conclusion = "CCONJ"
|
||||||
|
object.prevTag2 == "CCONJ" and object.prevTag1 == "ADV" : object.conclusion = "PART"
|
||||||
|
object.word == "А" and object.nextTag1 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "-" and object.word == "либо" : object.conclusion = "ADV"
|
||||||
|
object.prevTag1 == "SCONJ" : object.conclusion = "PART"
|
||||||
|
object.tag == "AUX" : object.conclusion = "AUX"
|
||||||
|
object.prevWord1 == "не" and object.word == "было" : object.conclusion = "VERB"
|
||||||
|
object.word == "стал" and object.nextTag1 == "VERB" : object.conclusion = "VERB"
|
||||||
|
object.nextTag1 == "ADP" : object.conclusion = "VERB"
|
||||||
|
object.prevWord1 == "," and object.nextWord1 == "в" : object.conclusion = "AUX"
|
||||||
|
object.prevTag1 == "NOUN" and object.word == "были" and object.nextTag1 == "ADP" : object.conclusion = "AUX"
|
||||||
|
object.prevTag1 == "CCONJ" : object.conclusion = "AUX"
|
||||||
|
object.word == "было" and object.nextTag1 == "NUM" : object.conclusion = "VERB"
|
||||||
|
object.prevWord2 == "," and object.word == "было" : object.conclusion = "AUX"
|
||||||
|
object.word == "стала" and object.nextTag1 == "VERB" : object.conclusion = "VERB"
|
||||||
|
object.prevTag1 == "PUNCT" and object.nextTag1 == "PUNCT" : object.conclusion = "VERB"
|
||||||
|
object.word == "стали" and object.nextTag1 == "VERB" : object.conclusion = "VERB"
|
||||||
|
object.word == "быть" and object.nextTag1 == "PART" : object.conclusion = "VERB"
|
||||||
|
object.prevTag1 == "PART" and object.nextTag1 == "PUNCT" : object.conclusion = "VERB"
|
||||||
|
object.tag == "ADJ" : object.conclusion = "ADJ"
|
||||||
|
object.prevTag1 == "PUNCT" and object.nextTag1 == "ADP" : object.conclusion = "VERB"
|
||||||
|
object.prevWord1 == "-" : object.conclusion = "ADJ"
|
||||||
|
object.prevWord1 == "--" : object.conclusion = "ADJ"
|
||||||
|
object.prevTag2 == "NOUN" and object.prevTag1 == "PUNCT" and object.word == "многие" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "ений" : object.conclusion = "NOUN"
|
||||||
|
object.nextWord1 == "-" : object.conclusion = "ADV"
|
||||||
|
object.nextWord2 == "либо" : object.conclusion = "DET"
|
||||||
|
object.suffixL3 == "ций" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag1 == "ADJ" and object.nextTag1 == "PUNCT" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "ных" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL2 == "ый" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL3 == "ное" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL2 == "го" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "аний" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "вший" : object.conclusion = "VERB"
|
||||||
|
object.word == "бывший" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "ющая" : object.conclusion = "VERB"
|
||||||
|
object.nextWord1 == "км" : object.conclusion = "NUM"
|
||||||
|
object.word == "кв." : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "ющих" : object.conclusion = "VERB"
|
||||||
|
object.word == "следующих" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "изму" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "вших" : object.conclusion = "VERB"
|
||||||
|
object.word == "бывших" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "вшим" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "ывая" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "емых" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "вшая" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "рий" : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "" : object.conclusion = "PROPN"
|
||||||
|
object.nextTag2 == "PUNCT" : object.conclusion = "PROPN"
|
||||||
|
object.prevTag2 == "PUNCT" and object.prevTag1 == "PART" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "зий" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL3 == "лий" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "дкой" : object.conclusion = "NOUN"
|
||||||
|
object.word == "я" and object.nextTag1 == "VERB" : object.conclusion = "PRON"
|
||||||
|
object.prevTag1 == "PUNCT" and object.nextTag1 == "DET" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "ивая" : object.conclusion = "VERB"
|
||||||
|
object.nextTag1 == "PROPN" : object.conclusion = "NOUN"
|
||||||
|
object.nextTag1 == "PRON" and object.nextTag2 == "NOUN" : object.conclusion = "VERB"
|
||||||
|
object.prevWord1 == "с" and object.nextWord1 == "." : object.conclusion = "NOUN"
|
||||||
|
object.prevWord1 == "семейства" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "иной" : object.conclusion = "NOUN"
|
||||||
|
object.word == "21" and object.nextWord2 == "." : object.conclusion = "NUM"
|
||||||
|
object.word == "14" and object.nextTag1 == "NOUN" and object.nextTag2 == "PUNCT" : object.conclusion = "NUM"
|
||||||
|
object.suffixL4 == "ющее" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "емые" : object.conclusion = "VERB"
|
||||||
|
object.suffixL3 == "жая" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "олго" : object.conclusion = "ADV"
|
||||||
|
object.suffixL4 == "рмой" : object.conclusion = "NOUN"
|
||||||
|
object.suffixL4 == "вкой" : object.conclusion = "NOUN"
|
||||||
|
object.nextTag1 == "AUX" and object.nextTag2 == "ADV" : object.conclusion = "PROPN"
|
||||||
|
object.prevWord2 == "названия" : object.conclusion = "PROPN"
|
||||||
|
object.word == "12" and object.nextTag1 == "PUNCT" : object.conclusion = "NUM"
|
||||||
|
object.word == "2005" and object.nextTag1 == "PUNCT" : object.conclusion = "NUM"
|
||||||
|
object.word == "14" and object.nextWord1 == "лет" : object.conclusion = "NUM"
|
||||||
|
object.suffixL4 == "ящих" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "ющим" : object.conclusion = "VERB"
|
||||||
|
object.nextTag1 == "NOUN" and object.nextTag2 == "ADP" : object.conclusion = "ADJ"
|
||||||
|
object.suffixL4 == "ящий" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "щему" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "упая" : object.conclusion = "VERB"
|
||||||
|
object.suffixL4 == "емой" : object.conclusion = "VERB"
|
||||||
|
object.nextTag1 == "ADV" and object.nextTag2 == "ADP" : object.conclusion = "VERB"
|
138443
Jonas_Solutions/ru_syntagrus-ud-dev.conllu
Normal file
138443
Jonas_Solutions/ru_syntagrus-ud-dev.conllu
Normal file
File diff suppressed because it is too large
Load Diff
136996
Jonas_Solutions/ru_syntagrus-ud-test.conllu
Normal file
136996
Jonas_Solutions/ru_syntagrus-ud-test.conllu
Normal file
File diff suppressed because it is too large
Load Diff
920335
Jonas_Solutions/ru_syntagrus-ud-train-uncommented.conllu
Normal file
920335
Jonas_Solutions/ru_syntagrus-ud-train-uncommented.conllu
Normal file
File diff suppressed because it is too large
Load Diff
1017963
Jonas_Solutions/ru_syntagrus-ud-train.conllu
Normal file
1017963
Jonas_Solutions/ru_syntagrus-ud-train.conllu
Normal file
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user