{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    },
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<script>\n",
       "  function code_toggle() {\n",
       "    if (code_shown){\n",
       "      $('div.input').hide('500');\n",
       "      $('#toggleButton').val('Show Code')\n",
       "    } else {\n",
       "      $('div.input').show('500');\n",
       "      $('#toggleButton').val('Hide Code')\n",
       "    }\n",
       "    code_shown = !code_shown\n",
       "  }\n",
       "\n",
       "  $( document ).ready(function(){\n",
       "    code_shown=false;\n",
       "    $('div.input').hide()\n",
       "  });\n",
       "</script>\n",
       "<form action=\"javascript:code_toggle()\"><input type=\"submit\" id=\"toggleButton\" value=\"Show Code\"></form>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%%html\n",
    "<script>\n",
    "  function code_toggle() {\n",
    "    if (code_shown){\n",
    "      $('div.input').hide('500');\n",
    "      $('#toggleButton').val('Show Code')\n",
    "    } else {\n",
    "      $('div.input').show('500');\n",
    "      $('#toggleButton').val('Hide Code')\n",
    "    }\n",
    "    code_shown = !code_shown\n",
    "  }\n",
    "\n",
    "  $( document ).ready(function(){\n",
    "    code_shown=false;\n",
    "    $('div.input').hide()\n",
    "  });\n",
    "</script>\n",
    "<form action=\"javascript:code_toggle()\"><input type=\"submit\" id=\"toggleButton\" value=\"Show Code\"></form>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Introduction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## What is NLP?\n",
    "\n",
    "* Building computer systems that **understand** and **generate** natural languages.\n",
    "* Deep understanding of **broad** language\n",
    "    * not just string processing or keyword matching\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Can you think of NLP Applications?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Chatbots\n",
    "\n",
    "![chatgpt_nlp_applications](../img/chatgpt_nlp_applications.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Speech Recognition?\n",
    "\n",
    "Speech Recognition is a challenging application, but is usually not considered NLP. We will not cover this topic here."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "![beach](../img/wreckanicebeach.png)\n",
    "\n",
    "recognise speech vs. wreck a nice beach\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Sentiment Analysis\n",
    "\n",
    "![sent](../img/sentiment_0.png)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Machine Translation\n",
    "\n",
    "![mt](mt_figures/avocado.png)\n",
    "\n",
    "http://translate.google.com/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Information Extraction\n",
    "![ie1](../img/ie1.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Information Extraction\n",
    "![ie2](../img/ie2.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Generation\n",
    "![gen](../img/shirtless2.jpeg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Generation\n",
    "![gen](../img/shirtless.jpeg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Reading Comprehension\n",
    "\n",
    "<center>\n",
    "<img src=\"../img/tydiqa_graupel.png\" width=\"600\"/>\n",
    "</center>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Personal Assistants\n",
    "<table><tr>\n",
    "<td> <img src=\"../img/siri-hates-eggs-photo-u1.jpg\" alt=\"Siri1\" style=\"width: 500px;\"/> </td>\n",
    "<td> <img src=\"../img/GoogleAssistantFail_07.jpg\" alt=\"Siri2\" style=\"width: 450px;\"/> </td>\n",
    "</tr></table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "<center><img src=\"../img/quiz_time.png\"></center>\n",
    "\n",
    "What is difficult about NLP?\n",
    "\n",
    "Discuss and enter your answers here:\n",
    "\n",
    "# [tinyurl.com/diku-nlp-q1](https://tinyurl.com/diku-nlp-q1)\n",
    "\n",
    "([Responses](https://docs.google.com/forms/d/121VI1BeO1TWuWXnAeQbHcBdMazQ3rPivoko29YyrZz4/edit#responses))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Ambiguity Everywhere\n",
    "\n",
    "* Fed <b>raises</b> interest rates 0.5% in effort to control inflation\n",
    "* Fed raises <b>interest</b> rates 0.5% in effort to control inflation\n",
    "* Fed raises interest <b>rates</b> 0.5% in effort to control inflation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Ambiguity Everywhere\n",
    "\n",
    "\"Jane ate spaghetti with a **silver spoon**.\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Do you mean..."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Jane used a silver spoon to eat spaghetti? (**cutlery**)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Jane had spaghetti and a silver spoon? (**part**)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Jane exhibited a silver spoon while eating spaghetti? (**manner**)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "Jane ate spaghetti in the presence of a silver spoon? (**company**)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "### Ambiguity on different linguistic levels\n",
    "\n",
    "<img src=\"../img/nlp_pyramid.png\" style=\"float:left;\" width=45%></img>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Core NLP Tasks\n",
    "* Tokenisation, Segmentation\n",
    "* Part of Speech Tagging\n",
    "* Language Modelling\n",
    "* Machine Translation\n",
    "* Syntactic and Semantic Parsing\n",
    "* Document Classification\n",
    "* Information Extraction\n",
    "* Question Answering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    },
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Core NLP Methods\n",
    "\n",
    "* Structured Prediction \n",
    "* Preprocessing\n",
    "* Generative Learning\n",
    "* Discriminative Learning\n",
    "* Weak Supervision\n",
    "* Representation and Deep Learning"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}