{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append(\"..\")\n",
    "import statnlpbook.util as util"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Introduction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## What is NLP?\n",
    "\n",
    "![dogs](../img/whatwesaytodogs.png)\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": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Can you think of NLP Applications?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Speech Recognition\n",
    "\n",
    "![beach](../img/wreckanicebeach.png)\n",
    "Speech Recognition is usually not considered NLP. We will not cover this topic here."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Machine Translation\n",
    "\n",
    "![mt](../img/mt.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Personal Assistants\n",
    "<img src=\"../img/siri1.png\" style=\"float:left;\" width=45%></img><img src=\"../img/siri2.png\" width=45%></img>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Information Extraction\n",
    "![ie1](../img/ie1.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Information Extraction\n",
    "![ie2](../img/ie2.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Summarization\n",
    "![sum](../img/summarization.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Generation\n",
    "![gen](../img/shirtless.jpeg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Question Answering\n",
    "![qa](../img/qa.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Sentiment Analysis\n",
    "\n",
    "![sent](../img/sentiment.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Machine Comprehension\n",
    "\n",
    "![mc](../img/comprehension.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Cognitive Science and Psycholinguistics \n",
    "\n",
    "![cog](../img/psycho.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Why is it difficult?\n",
    "\n",
    "![sailor_moon1](../img/sailor_moon1.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Why is it difficult?\n",
    "\n",
    "![sexcoffee](../img/sailor_moon2.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Structural Ambiguity\n",
    "\n",
    "[Play the Structural Ambiguity Game](http://madlyambiguous.osu.edu:1035/)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "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": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Fool a [Sentiment Analyzer](http://text-processing.com/demo/sentiment/)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### Fool a [Machine Translator](http://translate.google.com/?hl=en&tab=TT)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### [Count](https://books.google.com/ngrams) N-grams"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Syllabus\n",
    "\n",
    "* Structured Prediction \n",
    "* Preprocessing\n",
    "* Generative Learning\n",
    "* Discriminative Learning\n",
    "* Weak Supervision\n",
    "* Representation and Deep Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## NLP Tasks\n",
    "* Tokenization, Segmentation\n",
    "* Language Modelling\n",
    "* Machine Translation\n",
    "* Syntactic Parsing\n",
    "* Document Classification\n",
    "* Information Extraction\n",
    "* Textual Entailment/Machine Comprehension"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}