From 480c52d913fff811e23b8dc8b3fb42691bfa366b Mon Sep 17 00:00:00 2001
From: Michael Murtaugh <mm@automatist.org>
Date: Wed, 28 Oct 2020 10:19:09 +0100
Subject: [PATCH] added example to nltk-pos

---
 nltk-pos-tagger.ipynb | 47 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/nltk-pos-tagger.ipynb b/nltk-pos-tagger.ipynb
index a5bf536..1d03834 100644
--- a/nltk-pos-tagger.ipynb
+++ b/nltk-pos-tagger.ipynb
@@ -368,6 +368,53 @@
     "</td></tr></tbody></table>"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## A telling/tricky case\n",
+    "It's important to realize that POS tagging is not a fixed property of a word -- but depends on the context of each word. The NLTK book gives an example of [homonyms](http://www.nltk.org/book_1ed/ch05.html#using-a-tagger) -- words that are written the same, but are actually pronounced differently and have different meanings depending on their use."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('They', 'PRP'),\n",
+       " ('refuse', 'VBP'),\n",
+       " ('to', 'TO'),\n",
+       " ('permit', 'VB'),\n",
+       " ('us', 'PRP'),\n",
+       " ('to', 'TO'),\n",
+       " ('obtain', 'VB'),\n",
+       " ('the', 'DT'),\n",
+       " ('refuse', 'NN'),\n",
+       " ('permit', 'NN')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "text = nltk.word_tokenize(\"They refuse to permit us to obtain the refuse permit\")\n",
+    "nltk.pos_tag(text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "From the book:\n",
+    "\n",
+    "> Notice that refuse and permit both appear as a present tense verb (VBP) and a noun (NN). E.g. refUSE is a verb meaning \"deny,\" while REFuse is a noun meaning \"trash\" (i.e. they are not homophones). Thus, we need to know which word is being used in order to pronounce the text correctly. (For this reason, text-to-speech systems usually perform POS-tagging.)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},