diff --git a/docs/css/cookbook.css b/docs/css/cookbook.css
new file mode 100644
index 0000000..64e800b
--- /dev/null
+++ b/docs/css/cookbook.css
@@ -0,0 +1,96 @@
+/* https://stackoverflow.com/questions/56373198/get-xaringan-incremental-animations-to-print-to-pdf */
+
+.title-slide {
+  background-image: url(img/Dry_Chili_pepper.jpg);
+  /* background-position: 100% 0%; ## just start changing this */
+  background-size: 300px;
+  background-color: #fff;
+  padding-left: 100px;  /* delete this for 4:3 aspect ratio */
+}
+
+
+.remark-slide-content {
+    background-color: #FAFAFA;
+    border-top: 80px solid #6B84AC;
+    font-size: 20px;
+    font-weight: 300;
+    line-height: 1.5;
+    padding: 1em 2em 1em 2em;
+}
+
+hr, .title-slide h2::after, .mline h1::after {
+    content: '';
+    display: block;
+    border: none;
+    background-color: #efefef;
+    /* color: #EB811B; */
+    height: 3px;
+}
+@media print {
+  .has-continuation {
+    display: block !important;
+  }
+}
+
+.inverse {
+  background-color: #6B84AC;
+  border-top: 0px !important;
+  color: #ffffff;
+  /* text-shadow: 0 0 20px #333; */
+}
+
+
+.inverse h1{
+  margin-top: 425px;
+}
+
+.inverse2 h1{
+  margin-top: 100px;
+  text-align: right;
+}
+
+.inverse2 h2 {
+    color: #efefef;
+    text-align: right;
+}
+
+
+.title-slide h1 {
+    margin-top: 100px;
+    color: #efefef;
+}
+
+
+
+.title-slide h2 {
+    color: #efefef;
+}
+
+.title-slide h3 {
+    color: #efefef;
+}
+
+.white{
+  background-color: #ffffff !important;
+}
+
+h1 {
+  margin-top: -95px;
+  color: #efefef;
+  text-align: left;
+}
+
+.smallpic{
+  width: 2500px;
+  height: 180px
+}
+
+.attribution{
+  padding-left: 650px;
+  font-size: 15px;
+  color: #efefef;
+}
+
+.attribution a {
+  color: #efefef;
+}
\ No newline at end of file
diff --git a/docs/img/Dry_Chili_pepper.jpg b/docs/img/Dry_Chili_pepper.jpg
new file mode 100644
index 0000000..a31a994
Binary files /dev/null and b/docs/img/Dry_Chili_pepper.jpg differ
diff --git a/docs/img/Dry_tagliatelle_pasta.jpg b/docs/img/Dry_tagliatelle_pasta.jpg
new file mode 100644
index 0000000..d243147
Binary files /dev/null and b/docs/img/Dry_tagliatelle_pasta.jpg differ
diff --git a/docs/img/Making_potato_wedges.jpg b/docs/img/Making_potato_wedges.jpg
new file mode 100644
index 0000000..1377369
Binary files /dev/null and b/docs/img/Making_potato_wedges.jpg differ
diff --git a/docs/img/Oranges.jpg b/docs/img/Oranges.jpg
new file mode 100644
index 0000000..b7fc92f
Binary files /dev/null and b/docs/img/Oranges.jpg differ
diff --git a/docs/img/Spices.jpg b/docs/img/Spices.jpg
new file mode 100644
index 0000000..90ae879
Binary files /dev/null and b/docs/img/Spices.jpg differ
diff --git a/docs/index.Rmd b/docs/index.Rmd
new file mode 100644
index 0000000..eaddd2d
--- /dev/null
+++ b/docs/index.Rmd
@@ -0,0 +1,66 @@
+---
+title: "The PolMine Cookbook"
+author: "Andreas Blaette, Christoph Leonhardt"
+output: 
+  xaringan::moon_reader:
+    css: [default, metropolis, robot-fonts, './css/cookbook.css']
+    seal: false
+    nature:
+      countIncrementalSlides: false
+      titleSlideClass: ["title-slide", "nobackground", "inverse"]
+editor_options:
+  chunk_output_type: console
+---
+
+background-image: url(img/Oranges.jpg)
+background-size: cover
+class: nobackground, inverse
+
+.attribution[[Picture: Wikimedia Commons](https://commons.wikimedia.org/wiki/File:Oranges.jpg)]
+
+
+# Cookin' with PolMine
+## A Cookbook for Corpus Analysis
+
+---
+
+
+background-image: url(img/Spices.jpg)
+background-size: cover
+class: nobackground, inverse
+
+.attribution[[Ramesh NG](https://commons.wikimedia.org/wiki/File:Dry_Chili_pepper.jpg)]
+
+
+# The CQP Syntax
+## Spice up your Queries
+
+[Click here to see recipe!](subset.html)
+
+---
+
+background-image: url(img/Making_potato_wedges.jpg)
+background-size: cover
+class: nobackground, inverse2
+
+.attribution[[W. Carter](https://upload.wikimedia.org/wikipedia/commons/4/49/Making_potato_wedges.jpg)]
+
+
+# Corpus Slices
+## Subsetting by Structural Annotation
+
+[Click here to see recipe!](subset.html)
+
+---
+
+background-image: url(img/Dry_tagliatelle_pasta.jpg)
+background-size: cover
+class: nobackground, inverse
+
+.attribution[[Mathias Braux](https://upload.wikimedia.org/wikipedia/commons/3/32/Dry_tagliatelle_pasta.jpg)]
+
+# Textual Tagliatelle
+## Unraveling Sentence Annotation
+
+[Click here to see recipe!](sentences_intro.html)
+
diff --git a/docs/index.html b/docs/index.html
new file mode 100644
index 0000000..dc88397
--- /dev/null
+++ b/docs/index.html
@@ -0,0 +1,185 @@
+<!DOCTYPE html>
+<html lang="" xml:lang="">
+  <head>
+    <title>The PolMine Cookbook</title>
+    <meta charset="utf-8" />
+    <meta name="author" content="Andreas Blaette, Christoph Leonhardt" />
+    <script src="index_files/header-attrs-2.25/header-attrs.js"></script>
+    <link href="index_files/remark-css-0.0.1/default.css" rel="stylesheet" />
+    <link href="index_files/remark-css-0.0.1/metropolis.css" rel="stylesheet" />
+    <link href="index_files/remark-css-0.0.1/robot-fonts.css" rel="stylesheet" />
+    <link rel="stylesheet" href="css/cookbook.css" type="text/css" />
+  </head>
+  <body>
+    <textarea id="source">
+
+
+background-image: url(img/Oranges.jpg)
+background-size: cover
+class: nobackground, inverse
+
+.attribution[[Picture: Wikimedia Commons](https://commons.wikimedia.org/wiki/File:Oranges.jpg)]
+
+
+# Cookin' with PolMine
+## A Cookbook for Corpus Analysis
+
+---
+
+
+background-image: url(img/Spices.jpg)
+background-size: cover
+class: nobackground, inverse
+
+.attribution[[Ramesh NG](https://commons.wikimedia.org/wiki/File:Dry_Chili_pepper.jpg)]
+
+
+# The CQP Syntax
+## Spice up your Queries
+
+[Click here to see recipe!](subset.html)
+
+---
+
+background-image: url(img/Making_potato_wedges.jpg)
+background-size: cover
+class: nobackground, inverse2
+
+.attribution[[W. Carter](https://upload.wikimedia.org/wikipedia/commons/4/49/Making_potato_wedges.jpg)]
+
+
+# Corpus Slices
+## Subsetting by Structural Annotation
+
+[Click here to see recipe!](subset.html)
+
+---
+
+background-image: url(img/Dry_tagliatelle_pasta.jpg)
+background-size: cover
+class: nobackground, inverse
+
+.attribution[[Mathias Braux](https://upload.wikimedia.org/wikipedia/commons/3/32/Dry_tagliatelle_pasta.jpg)]
+
+# Textual Tagliatelle
+## Unraveling Sentence Annotation
+
+[Click here to see recipe!](sentences_intro.html)
+
+    </textarea>
+<style data-target="print-only">@media screen {.remark-slide-container{display:block;}.remark-slide-scaler{box-shadow:none;}}</style>
+<script src="https://remarkjs.com/downloads/remark-latest.min.js"></script>
+<script>var slideshow = remark.create({
+"countIncrementalSlides": false
+});
+if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {
+  window.dispatchEvent(new Event('resize'));
+});
+(function(d) {
+  var s = d.createElement("style"), r = d.querySelector(".remark-slide-scaler");
+  if (!r) return;
+  s.type = "text/css"; s.innerHTML = "@page {size: " + r.style.width + " " + r.style.height +"; }";
+  d.head.appendChild(s);
+})(document);
+
+(function(d) {
+  var el = d.getElementsByClassName("remark-slides-area");
+  if (!el) return;
+  var slide, slides = slideshow.getSlides(), els = el[0].children;
+  for (var i = 1; i < slides.length; i++) {
+    slide = slides[i];
+    if (slide.properties.continued === "true" || slide.properties.count === "false") {
+      els[i - 1].className += ' has-continuation';
+    }
+  }
+  var s = d.createElement("style");
+  s.type = "text/css"; s.innerHTML = "@media print { .has-continuation { display: none; } }";
+  d.head.appendChild(s);
+})(document);
+// delete the temporary CSS (for displaying all slides initially) when the user
+// starts to view slides
+(function() {
+  var deleted = false;
+  slideshow.on('beforeShowSlide', function(slide) {
+    if (deleted) return;
+    var sheets = document.styleSheets, node;
+    for (var i = 0; i < sheets.length; i++) {
+      node = sheets[i].ownerNode;
+      if (node.dataset["target"] !== "print-only") continue;
+      node.parentNode.removeChild(node);
+    }
+    deleted = true;
+  });
+})();
+// add `data-at-shortcutkeys` attribute to <body> to resolve conflicts with JAWS
+// screen reader (see PR #262)
+(function(d) {
+  let res = {};
+  d.querySelectorAll('.remark-help-content table tr').forEach(tr => {
+    const t = tr.querySelector('td:nth-child(2)').innerText;
+    tr.querySelectorAll('td:first-child .key').forEach(key => {
+      const k = key.innerText;
+      if (/^[a-z]$/.test(k)) res[k] = t;  // must be a single letter (key)
+    });
+  });
+  d.body.setAttribute('data-at-shortcutkeys', JSON.stringify(res));
+})(document);
+(function() {
+  "use strict"
+  // Replace <script> tags in slides area to make them executable
+  var scripts = document.querySelectorAll(
+    '.remark-slides-area .remark-slide-container script'
+  );
+  if (!scripts.length) return;
+  for (var i = 0; i < scripts.length; i++) {
+    var s = document.createElement('script');
+    var code = document.createTextNode(scripts[i].textContent);
+    s.appendChild(code);
+    var scriptAttrs = scripts[i].attributes;
+    for (var j = 0; j < scriptAttrs.length; j++) {
+      s.setAttribute(scriptAttrs[j].name, scriptAttrs[j].value);
+    }
+    scripts[i].parentElement.replaceChild(s, scripts[i]);
+  }
+})();
+(function() {
+  var links = document.getElementsByTagName('a');
+  for (var i = 0; i < links.length; i++) {
+    if (/^(https?:)?\/\//.test(links[i].getAttribute('href'))) {
+      links[i].target = '_blank';
+    }
+  }
+})();</script>
+
+<script>
+slideshow._releaseMath = function(el) {
+  var i, text, code, codes = el.getElementsByTagName('code');
+  for (i = 0; i < codes.length;) {
+    code = codes[i];
+    if (code.parentNode.tagName !== 'PRE' && code.childElementCount === 0) {
+      text = code.textContent;
+      if (/^\\\((.|\s)+\\\)$/.test(text) || /^\\\[(.|\s)+\\\]$/.test(text) ||
+          /^\$\$(.|\s)+\$\$$/.test(text) ||
+          /^\\begin\{([^}]+)\}(.|\s)+\\end\{[^}]+\}$/.test(text)) {
+        code.outerHTML = code.innerHTML;  // remove <code></code>
+        continue;
+      }
+    }
+    i++;
+  }
+};
+slideshow._releaseMath(document);
+</script>
+<!-- dynamically load mathjax for compatibility with self-contained -->
+<script>
+(function () {
+  var script = document.createElement('script');
+  script.type = 'text/javascript';
+  script.src  = 'https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-MML-AM_CHTML';
+  if (location.protocol !== 'file:' && /^https?:/.test(script.src))
+    script.src  = script.src.replace(/^https?:/, '');
+  document.getElementsByTagName('head')[0].appendChild(script);
+})();
+</script>
+  </body>
+</html>
diff --git a/docs/index_files/header-attrs-2.25/header-attrs.js b/docs/index_files/header-attrs-2.25/header-attrs.js
new file mode 100644
index 0000000..dd57d92
--- /dev/null
+++ b/docs/index_files/header-attrs-2.25/header-attrs.js
@@ -0,0 +1,12 @@
+// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
+// be compatible with the behavior of Pandoc < 2.8).
+document.addEventListener('DOMContentLoaded', function(e) {
+  var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
+  var i, h, a;
+  for (i = 0; i < hs.length; i++) {
+    h = hs[i];
+    if (!/^h[1-6]$/i.test(h.tagName)) continue;  // it should be a header h1-h6
+    a = h.attributes;
+    while (a.length > 0) h.removeAttribute(a[0].name);
+  }
+});
diff --git a/docs/index_files/remark-css-0.0.1/default.css b/docs/index_files/remark-css-0.0.1/default.css
new file mode 100644
index 0000000..d37bfd2
--- /dev/null
+++ b/docs/index_files/remark-css-0.0.1/default.css
@@ -0,0 +1,72 @@
+a, a > code {
+  color: rgb(249, 38, 114);
+  text-decoration: none;
+}
+.footnote {
+  position: absolute;
+  bottom: 3em;
+  padding-right: 4em;
+  font-size: 90%;
+}
+.remark-code-line-highlighted     { background-color: #ffff88; }
+
+.inverse {
+  background-color: #272822;
+  color: #d6d6d6;
+  text-shadow: 0 0 20px #333;
+}
+.inverse h1, .inverse h2, .inverse h3 {
+  color: #f3f3f3;
+}
+/* Two-column layout */
+.left-column {
+  color: #777;
+  width: 20%;
+  height: 92%;
+  float: left;
+}
+.left-column h2:last-of-type, .left-column h3:last-child {
+  color: #000;
+}
+.right-column {
+  width: 75%;
+  float: right;
+  padding-top: 1em;
+}
+.pull-left {
+  float: left;
+  width: 47%;
+}
+.pull-right {
+  float: right;
+  width: 47%;
+}
+.pull-right + * {
+  clear: both;
+}
+img, video, iframe {
+  max-width: 100%;
+}
+blockquote {
+  border-left: solid 5px lightgray;
+  padding-left: 1em;
+}
+.remark-slide table {
+  margin: auto;
+  border-top: 1px solid #666;
+  border-bottom: 1px solid #666;
+}
+.remark-slide table thead th { border-bottom: 1px solid #ddd; }
+th, td { padding: 5px; }
+.remark-slide thead, .remark-slide tfoot, .remark-slide tr:nth-child(even) { background: #eee }
+
+@page { margin: 0; }
+@media print {
+  .remark-slide-scaler {
+    width: 100% !important;
+    height: 100% !important;
+    transform: scale(1) !important;
+    top: 0 !important;
+    left: 0 !important;
+  }
+}
diff --git a/docs/index_files/remark-css-0.0.1/metropolis.css b/docs/index_files/remark-css-0.0.1/metropolis.css
new file mode 100644
index 0000000..59f0072
--- /dev/null
+++ b/docs/index_files/remark-css-0.0.1/metropolis.css
@@ -0,0 +1,254 @@
+.remark-slide-content {
+  background-color: #FAFAFA;
+  border-top: 80px solid #23373B;
+  font-size: 20px;
+  font-weight: 300;
+  line-height: 1.5;
+  padding: 1em 2em 1em 2em
+}
+
+.title-slide .inverse .remark-slide-content {
+  background-color: #FAFAFA;
+}
+
+.inverse {
+  background-color: #23373B;
+  text-shadow: none;
+}
+
+/* Removes colored bar from top of the slide resulting in a clear slide */
+.clear{
+  border-top: 0px solid #FAFAFA;
+}
+
+h1 {
+  font-weight: normal;
+  margin-top: -95px;
+  margin-left: -00px;
+  color: #FAFAFA;
+}
+
+h2, h3, h4 {
+  padding-top: -15px;
+  padding-bottom: 00px;
+  color: #1A292C;
+  text-shadow: none;
+  font-weight: 400;
+  text-align: left;
+  margin-left: 00px;
+  margin-bottom: -10px;
+}
+
+.remark-slide-content h1 {
+  font-size: 45px;
+}
+
+.remark-slide-content h2 {
+  font-size: 35px;
+}
+
+.remark-slide-content h3 {
+  font-size: 30px;
+}
+
+.left-column h2, .left-column h3, .left-column h4 {
+  color: #777;
+}
+
+.left-column h2:last-of-type, .left-column h3:last-child {
+  color: #1A292C;
+}
+
+.title-slide {
+  background-color: #FAFAFA;
+  border-top: 80px solid #FAFAFA;
+}
+
+.title-slide h1  {
+  color: #1A292C;
+  font-size: 40px;
+  text-shadow: none;
+  font-weight: 400;
+  text-align: left;
+  margin-left: 15px;
+  padding-top: 80px;
+}
+.title-slide h2  {
+  margin-top: -25px;
+  padding-bottom: -20px;
+  color: #1A292C;
+  text-shadow: none;
+  font-weight: 300;
+  font-size: 35px;
+  text-align: left;
+  margin-left: 15px;
+}
+.title-slide h3  {
+  color: #1A292C;
+  text-shadow: none;
+  font-weight: 300;
+  font-size: 25px;
+  text-align: left;
+  margin-left: 15px;
+  margin-bottom: -30px;
+}
+
+hr, .title-slide h2::after, .mline h1::after {
+  content: '';
+  display: block;
+  border: none;
+  background-color: #EB811B;
+  color: #EB811B;
+  height: 1px;
+}
+
+hr, .mline h1::after {
+  margin: 1em 15px 0 15px;
+}
+
+.title-slide h2::after {
+  margin: 10px 15px 35px 0;
+}
+
+.mline h1::after {
+  margin: 10px 15px 0 15px;
+}
+
+.remark-slide-number {
+  font-size: 13pt;
+  color: #272822;
+  opacity: 1;
+}
+.inverse .remark-slide-number {
+  font-size: 13pt;
+  color: #FAFAFA;
+  opacity: 1;
+}
+
+/* turns off slide numbers for title page: https://github.com/gnab/remark/issues/298 */
+.title-slide .remark-slide-number {
+  display: none;
+}
+
+.remark-inline-code {
+  /* background: #F5F5F5; /* lighter */
+  background: #e7e8e2; /* darker */
+  border-radius: 3px;
+  padding: 4px;
+}
+
+.code10 .remark-code {
+  font-size: 10%;
+}
+
+.code20 .remark-code {
+  font-size: 20%;
+}
+
+.code30 .remark-code {
+  font-size: 30%;
+}
+
+.code40 .remark-code {
+  font-size: 40%;
+}
+
+.code50 .remark-code {
+  font-size: 50%;
+}
+
+.code60 .remark-code {
+  font-size: 60%;
+}
+
+.code70 .remark-code {
+  font-size: 70%;
+}
+
+.code80 .remark-code {
+  font-size: 80%;
+}
+
+.code90 .remark-code {
+  font-size: 90%;
+}
+
+.code100 .remark-code {
+  font-size: 100%;
+}
+
+.font10 {
+  font-size: 10%;
+}
+
+.font20 {
+  font-size: 20%;
+}
+
+.font30 {
+  font-size: 30%;
+}
+
+.font40 {
+  font-size: 40%;
+}
+
+.font50 {
+  font-size: 50%;
+}
+
+.font60 {
+  font-size: 60%;
+}
+
+.font70 {
+  font-size: 70%;
+}
+
+.font80 {
+  font-size: 80%;
+}
+
+.font90 {
+  font-size: 90%;
+}
+
+.font100 {
+  font-size: 100%;
+}
+
+.font110 {
+  font-size: 110%;
+}
+
+.font120 {
+  font-size: 120%;
+}
+
+.font130 {
+  font-size: 130%;
+}
+
+.font140 {
+  font-size: 140%;
+}
+
+.font150 {
+  font-size: 150%;
+}
+
+.font160 {
+  font-size: 160%;
+}
+.font170 {
+  font-size: 170%;
+}
+.font180 {
+  font-size: 180%;
+}
+.font190 {
+  font-size: 190%;
+}
+.font200 {
+  font-size: 200%;
+}
diff --git a/docs/index_files/remark-css-0.0.1/robot-fonts.css b/docs/index_files/remark-css-0.0.1/robot-fonts.css
new file mode 100644
index 0000000..8e8c7b6
--- /dev/null
+++ b/docs/index_files/remark-css-0.0.1/robot-fonts.css
@@ -0,0 +1,19 @@
+@import url(https://fonts.googleapis.com/css?family=Inconsolata);
+@import url('https://fonts.googleapis.com/css?family=Roboto+Condensed:400,400i,700');
+@import url('https://fonts.googleapis.com/css?family=Roboto:700');
+
+body {
+  font-family: 'Roboto Condensed', 'Avenir Next', 'Helvetica Neue', 'Helvetica', sans-serif;
+  font-weight: 400;
+  color: #222;
+}
+.remark-slide-content {
+  font-size: 1.38em;
+  padding: .25em 3.5em .25em 4em;
+}
+h1, h2, h3 {
+  font-family: 'Roboto', 'Avenir Next', 'Helvetica Neue', 'Helvetica', sans-serif;
+  font-weight: 700;
+  color: #222;
+}
+.remark-code, .remark-inline-code { font-family: 'Inconsolata', 'Consolas', Monaco, monospace; }
diff --git a/sentences_intro.html b/sentences_intro.html
new file mode 100644
index 0000000..04acc16
--- /dev/null
+++ b/sentences_intro.html
@@ -0,0 +1,509 @@
+<!DOCTYPE html>
+<html lang="" xml:lang="">
+  <head>
+    <title>Cooking with GermaParl</title>
+    <meta charset="utf-8" />
+    <meta name="date" content="2023-12-14" />
+    <script src="sentences_intro_files/header-attrs-2.25/header-attrs.js"></script>
+    <link rel="stylesheet" href="css/default.css" type="text/css" />
+    <link rel="stylesheet" href="css/metropolis.css" type="text/css" />
+    <link rel="stylesheet" href="css/robot-fonts.css" type="text/css" />
+    <link rel="stylesheet" href="css/polminify.css" type="text/css" />
+  </head>
+  <body>
+    <textarea id="source">
+class: center, middle, inverse, title-slide
+
+.title[
+# Cooking with GermaParl
+]
+.date[
+### 2023-12-14
+]
+
+---
+
+
+
+
+# Purpose and Motivation
+
+* GermaParl2 comprises **rich structural annotation** on the level of protocols (such as the date or the legislative period) and the level of speakers (such as a speakers name or parliamentary group)
+
+* as seen in previous cookbooks, these can be used to **create meaningful subcorpora** for substantive analysis
+
+* but even beyond that, the corpus contains **annotation below the level of speeches** in forms of paragraph and sentence annotation
+
+* sentences can provide natural **units of analysis** with semantic meaning (for a comprehensive discussion see Däubler et al. 2012)
+
+* sentence annotations can be used for a variety of **use cases**
+
+---
+
+# Encoding of Sentences
+
+* sentences are annotated using **Stanford CoreNLP** (https://stanfordnlp.github.io/CoreNLP/)
+
+* sentences are encoded as the **structural attribute** `s` in GermaParl2
+
+* in contrast to other annotations in GermaParl, the sentence annotation **does not have values**; they describe regions in terms of start and end positions of sentences
+
+* `polmineR` indicates the missing values when called with `s_attributes()`:
+
+
+```r
+s_attributes("GERMAPARL2", "s")
+```
+
+```
+## ! s-attribute `s` does not have values, returning NA
+```
+
+```
+## [1] NA
+```
+
+---
+
+# Sentences and the tree structure 
+
+
+```r
+corpus("GERMAPARL2") %&gt;% polmineR::tree_structure()
+```
+
+```
+## protocol [lp│no│date│year│url│filetype]
+##    | 
+##    └─ speaker [who│name│party│parlgroup│role]
+##       | 
+##       └─ p [type]
+##          | 
+##          └─ s
+##             | 
+##             └─ ne [type]
+```
+
+---
+
+# Splitting Objects into Sentences
+
+`polmineR` makes it easy to split a (sub)corpus into sentences
+
+
+```r
+sentences &lt;- corpus("GERMAPARL2") |&gt;
+  subset(protocol_date == "1949-12-14") |&gt;
+  split(s_attribute = "s", values = FALSE)
+```
+
+* the `values` argument of `split()` makes missing **values** explicit, but this is not strictly necessary
+
+* the output is a bundle of subcorpora, each containing a single sentence
+
+* splitting by sentences can also be done for corpora with sentence annotation (caution: GermaParl2 is quite large)
+
+---
+
+# Splitting Objects into Sentences
+ 
+* subcorpus bundles can be used as usual
+
+* one example would be to decode the sentences as strings in their word order for further analysis
+
+* this could be useful for word embeddings or classification tasks which rely on word order
+
+
+```r
+sentences_ts &lt;- get_token_stream(sentences)
+```
+
+* the sentence annotation is not always perfect though:
+
+
+```r
+sentences_ts[[693]]
+```
+
+```
+## [1] "—"        "Ich"      "schließe" "die"      "23"       "."
+```
+
+
+```r
+sentences_ts[[694]]
+```
+
+```
+## [1] "Sitzung"    "des"        "Deutschen"  "Bundestags" "."
+```
+
+---
+
+# Sentence-Term-Matrices
+
+* the sentence bundle can also be used as input to create a **Document-Term-Matrix** (in this case a sentence-term-matrix)
+* potentially useful for **machine learning approaches** which rely on a **Bag-of-Words** representation of sentences
+* examples: Sentence Similarity, Weighting of Terms
+
+
+```r
+dtm &lt;- polmineR::as.DocumentTermMatrix(sentences, p_attribute = "word")
+```
+
+---
+
+# Sentence-Term-Matrices
+
+
+```r
+tm::inspect(dtm)
+```
+
+```
+## &lt;&lt;DocumentTermMatrix (documents: 695, terms: 3255)&gt;&gt;
+## Non-/sparse entries: 13796/2248429
+## Sparsity           : 99%
+## Maximal term length: 32
+## Weighting          : term frequency (tf)
+## Sample             :
+##        Terms
+## Docs     , . daß den der des die in und zu
+##   36563 38 1   0   0   0   0   2  0   0  0
+##   36589  8 1   1   1   4   0   2  3   2  1
+##   36619  9 1   2   3  12   0   2  2   2  2
+##   36643  7 1   0   0   1   1   2  1   0  1
+##   36674  8 1   3   1   3   0   4  3   4  1
+##   36695 10 1   4   0   3   1   4  1   3  0
+##   36717  5 1   3   0   2   1   0  2   1  1
+##   36733  5 1   0   1   2   2   2  2   3  0
+##   36777  5 1   1   0   4   2   7  1   4  0
+##   36787  6 1   1   1   4   0   0  3   2  1
+```
+
+---
+
+
+# Using Sentences as Context Windows
+
+* the boundaries of sentences can be used to define **context windows** of query terms
+
+* this can be useful to limit the analysis to relevant context words or to identify meaningful multi-word query terms
+
+* `polmineR` provides two ways to make use of the sentence annotation in these scenarios:
+
+#### 1) Sentence Annotation as a `boundary`:
+
+* the maximum number of tokens in the context window is determined by the values of `left` and `right` but the context does not extend over the boundary of a sentence
+
+
+```r
+corpus("GERMAPARL2") |&gt;
+  kwic(query = "Demokratie",
+       boundary = "s",
+       left = 20,
+       right = 20)
+```
+
+---
+
+# Using Sentences as Context Windows
+
+#### 2) Sentence Annotation as Context
+
+* the context window is determined by the **structural attribute** - here `s` - defined by `region` and a number of sentences in `left` and `right`
+  
+
+```r
+corpus("GERMAPARL2") |&gt;
+  kwic(query = "Demokratie",
+       region = "s",
+       left = 0,
+       right = 0)
+```
+
+* the annotation of `left` and `right` determines **additional context** in terms of sentences `s`
+
+* i.e. if `s` = 0, then the context window comprises of the same sentence as the query term
+
+---
+
+# Using Sentences as Context Windows
+
+* changing the values of `left` and `right` to 1 adds one additional sentence as context
+
+
+```r
+corpus("GERMAPARL2") |&gt;
+  kwic(query = "Demokratie",
+       region = "s",
+       left = 1,
+       right = 1)
+```
+
+* this is equivalent to the following syntax:
+
+
+```r
+corpus("GERMAPARL2") |&gt;
+  kwic(query = "Demokratie",
+       left = c("s" = 1),
+       right = c("s" = 1))
+```
+
+---
+
+# Using Sentences as Context Windows
+
+* this also applies to values passed to other parameters such as `positivelist` and `stoplist`: 
+
+
+```r
+corpus("GERMAPARL2") |&gt;
+  kwic(query = "Demokratie",
+       region = "s",
+       left = 0,
+       right = 0,
+       positivelist = "Krise"
+  )
+```
+
+```
+## ... filtering by positivelist
+```
+
+```
+## ... number of hits dropped due to positivelist: 37002
+```
+
+```
+## ... update count statistics for slot cpos
+```
+
+**Note:** Sentences which contain a query term more than once show up in the output of `kwic` more than once
+
+---
+
+# Using Sentences in CQP Queries
+
+* as noted in the CQP manual, "most linguistic queries should include the restriction within s to avoid crossing sentence boundaries" (https://cwb.sourceforge.io/files/CQP_Manual/4_2.html)
+
+* this can be achieved with the syntax used in the following query (results on the next slide)
+
+
+```r
+sc &lt;- corpus("GERMAPARL2") |&gt; subset(protocol_lp == 15)
+
+count(sc,
+      query = '"Bundesministerium.*" []{1,5} [xpos = "NN"] within s',
+      cqp = TRUE,
+      breakdown = TRUE)
+```
+
+* it has to be noted that this can be computationally expensive and depending on the use case, the differences are subtle
+
+---
+
+# Using Sentences in CQP Queries
+
+&lt;table&gt;
+&lt;caption&gt;First five Query Matches in GermaParl2, 15th Legislative Period&lt;/caption&gt;
+ &lt;thead&gt;
+  &lt;tr&gt;
+   &lt;th style="text-align:left;"&gt; query &lt;/th&gt;
+   &lt;th style="text-align:left;"&gt; match &lt;/th&gt;
+   &lt;th style="text-align:right;"&gt; count &lt;/th&gt;
+   &lt;th style="text-align:right;"&gt; share &lt;/th&gt;
+  &lt;/tr&gt;
+ &lt;/thead&gt;
+&lt;tbody&gt;
+  &lt;tr&gt;
+   &lt;td style="text-align:left;"&gt; &amp;quot;Bundesministerium.*&amp;quot; []{1,5} [xpos = &amp;quot;NN&amp;quot;] within s &lt;/td&gt;
+   &lt;td style="text-align:left;"&gt; Bundesministeriums für Wirtschaft &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 84 &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 6.78 &lt;/td&gt;
+  &lt;/tr&gt;
+  &lt;tr&gt;
+   &lt;td style="text-align:left;"&gt; &amp;quot;Bundesministerium.*&amp;quot; []{1,5} [xpos = &amp;quot;NN&amp;quot;] within s &lt;/td&gt;
+   &lt;td style="text-align:left;"&gt; Bundesministeriums für Verkehr &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 71 &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 5.73 &lt;/td&gt;
+  &lt;/tr&gt;
+  &lt;tr&gt;
+   &lt;td style="text-align:left;"&gt; &amp;quot;Bundesministerium.*&amp;quot; []{1,5} [xpos = &amp;quot;NN&amp;quot;] within s &lt;/td&gt;
+   &lt;td style="text-align:left;"&gt; Bundesministeriums des Innern &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 67 &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 5.41 &lt;/td&gt;
+  &lt;/tr&gt;
+  &lt;tr&gt;
+   &lt;td style="text-align:left;"&gt; &amp;quot;Bundesministerium.*&amp;quot; []{1,5} [xpos = &amp;quot;NN&amp;quot;] within s &lt;/td&gt;
+   &lt;td style="text-align:left;"&gt; Bundesministeriums der Finanzen &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 66 &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 5.33 &lt;/td&gt;
+  &lt;/tr&gt;
+  &lt;tr&gt;
+   &lt;td style="text-align:left;"&gt; &amp;quot;Bundesministerium.*&amp;quot; []{1,5} [xpos = &amp;quot;NN&amp;quot;] within s &lt;/td&gt;
+   &lt;td style="text-align:left;"&gt; Bundesministeriums für Gesundheit &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 66 &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 5.33 &lt;/td&gt;
+  &lt;/tr&gt;
+  &lt;tr&gt;
+   &lt;td style="text-align:left;"&gt; &amp;quot;Bundesministerium.*&amp;quot; []{1,5} [xpos = &amp;quot;NN&amp;quot;] within s &lt;/td&gt;
+   &lt;td style="text-align:left;"&gt; Bundesministerium des Innern &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 61 &lt;/td&gt;
+   &lt;td style="text-align:right;"&gt; 4.92 &lt;/td&gt;
+  &lt;/tr&gt;
+&lt;/tbody&gt;
+&lt;/table&gt;
+
+
+---
+
+# Sampling at the sentence level
+
+
+```r
+packageVersion("polmineR")
+```
+
+```
+## [1] '0.8.9.9001'
+```
+
+```r
+demsent_ids &lt;- corpus("GERMAPARL2") %&gt;%
+  hits(query = "Demokratie", s_attribute = "s", decode = FALSE) %&gt;%
+  as.data.frame() %&gt;%
+  pull(s)
+
+demsents &lt;- corpus("GERMAPARL2") %&gt;%
+  subset(s %in% !!demsent_ids) %&gt;%
+  split(s_attribute = "s") %&gt;%
+  get_token_stream(p_attribute = "word", collapse = " ")
+```
+
+* write it on disk and use it as input for ... whatsoever!
+
+
+---
+
+# References
+
+Däubler, T., Benoit, K., Mikhaylov, S., &amp; Laver, M. (2012). Natural Sentences as Valid Units for Coded Political Texts. British Journal of Political Science, 42(4), 937–951. http://www.jstor.org/stable/23274173.
+    </textarea>
+<style data-target="print-only">@media screen {.remark-slide-container{display:block;}.remark-slide-scaler{box-shadow:none;}}</style>
+<script src="https://remarkjs.com/downloads/remark-latest.min.js"></script>
+<script>var slideshow = remark.create({
+"countIncrementalSlides": false
+});
+if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {
+  window.dispatchEvent(new Event('resize'));
+});
+(function(d) {
+  var s = d.createElement("style"), r = d.querySelector(".remark-slide-scaler");
+  if (!r) return;
+  s.type = "text/css"; s.innerHTML = "@page {size: " + r.style.width + " " + r.style.height +"; }";
+  d.head.appendChild(s);
+})(document);
+
+(function(d) {
+  var el = d.getElementsByClassName("remark-slides-area");
+  if (!el) return;
+  var slide, slides = slideshow.getSlides(), els = el[0].children;
+  for (var i = 1; i < slides.length; i++) {
+    slide = slides[i];
+    if (slide.properties.continued === "true" || slide.properties.count === "false") {
+      els[i - 1].className += ' has-continuation';
+    }
+  }
+  var s = d.createElement("style");
+  s.type = "text/css"; s.innerHTML = "@media print { .has-continuation { display: none; } }";
+  d.head.appendChild(s);
+})(document);
+// delete the temporary CSS (for displaying all slides initially) when the user
+// starts to view slides
+(function() {
+  var deleted = false;
+  slideshow.on('beforeShowSlide', function(slide) {
+    if (deleted) return;
+    var sheets = document.styleSheets, node;
+    for (var i = 0; i < sheets.length; i++) {
+      node = sheets[i].ownerNode;
+      if (node.dataset["target"] !== "print-only") continue;
+      node.parentNode.removeChild(node);
+    }
+    deleted = true;
+  });
+})();
+// add `data-at-shortcutkeys` attribute to <body> to resolve conflicts with JAWS
+// screen reader (see PR #262)
+(function(d) {
+  let res = {};
+  d.querySelectorAll('.remark-help-content table tr').forEach(tr => {
+    const t = tr.querySelector('td:nth-child(2)').innerText;
+    tr.querySelectorAll('td:first-child .key').forEach(key => {
+      const k = key.innerText;
+      if (/^[a-z]$/.test(k)) res[k] = t;  // must be a single letter (key)
+    });
+  });
+  d.body.setAttribute('data-at-shortcutkeys', JSON.stringify(res));
+})(document);
+(function() {
+  "use strict"
+  // Replace <script> tags in slides area to make them executable
+  var scripts = document.querySelectorAll(
+    '.remark-slides-area .remark-slide-container script'
+  );
+  if (!scripts.length) return;
+  for (var i = 0; i < scripts.length; i++) {
+    var s = document.createElement('script');
+    var code = document.createTextNode(scripts[i].textContent);
+    s.appendChild(code);
+    var scriptAttrs = scripts[i].attributes;
+    for (var j = 0; j < scriptAttrs.length; j++) {
+      s.setAttribute(scriptAttrs[j].name, scriptAttrs[j].value);
+    }
+    scripts[i].parentElement.replaceChild(s, scripts[i]);
+  }
+})();
+(function() {
+  var links = document.getElementsByTagName('a');
+  for (var i = 0; i < links.length; i++) {
+    if (/^(https?:)?\/\//.test(links[i].getAttribute('href'))) {
+      links[i].target = '_blank';
+    }
+  }
+})();</script>
+
+<script>
+slideshow._releaseMath = function(el) {
+  var i, text, code, codes = el.getElementsByTagName('code');
+  for (i = 0; i < codes.length;) {
+    code = codes[i];
+    if (code.parentNode.tagName !== 'PRE' && code.childElementCount === 0) {
+      text = code.textContent;
+      if (/^\\\((.|\s)+\\\)$/.test(text) || /^\\\[(.|\s)+\\\]$/.test(text) ||
+          /^\$\$(.|\s)+\$\$$/.test(text) ||
+          /^\\begin\{([^}]+)\}(.|\s)+\\end\{[^}]+\}$/.test(text)) {
+        code.outerHTML = code.innerHTML;  // remove <code></code>
+        continue;
+      }
+    }
+    i++;
+  }
+};
+slideshow._releaseMath(document);
+</script>
+<!-- dynamically load mathjax for compatibility with self-contained -->
+<script>
+(function () {
+  var script = document.createElement('script');
+  script.type = 'text/javascript';
+  script.src  = 'https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-MML-AM_CHTML';
+  if (location.protocol !== 'file:' && /^https?:/.test(script.src))
+    script.src  = script.src.replace(/^https?:/, '');
+  document.getElementsByTagName('head')[0].appendChild(script);
+})();
+</script>
+  </body>
+</html>
diff --git a/sentences_intro_files/header-attrs-2.25/header-attrs.js b/sentences_intro_files/header-attrs-2.25/header-attrs.js
new file mode 100644
index 0000000..dd57d92
--- /dev/null
+++ b/sentences_intro_files/header-attrs-2.25/header-attrs.js
@@ -0,0 +1,12 @@
+// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
+// be compatible with the behavior of Pandoc < 2.8).
+document.addEventListener('DOMContentLoaded', function(e) {
+  var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
+  var i, h, a;
+  for (i = 0; i < hs.length; i++) {
+    h = hs[i];
+    if (!/^h[1-6]$/i.test(h.tagName)) continue;  // it should be a header h1-h6
+    a = h.attributes;
+    while (a.length > 0) h.removeAttribute(a[0].name);
+  }
+});