<?xml version="1.0" encoding="utf-8"?><!DOCTYPE article  PUBLIC '-//OASIS//DTD DocBook XML V4.4//EN'  'http://www.docbook.org/xml/4.4/docbookx.dtd'><article><articleinfo><title>PSC</title><revhistory><revision><revnumber>74</revnumber><date>2018-11-06 13:14:13</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>73</revnumber><date>2018-11-06 13:13:55</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>72</revnumber><date>2018-09-03 16:00:31</date><authorinitials>BartlomiejNiton</authorinitials></revision><revision><revnumber>71</revnumber><date>2018-09-03 15:57:16</date><authorinitials>BartlomiejNiton</authorinitials></revision><revision><revnumber>70</revnumber><date>2017-10-17 15:33:10</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>69</revnumber><date>2017-03-02 15:11:02</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>68</revnumber><date>2017-03-02 15:09:49</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>67</revnumber><date>2017-02-28 11:45:02</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>66</revnumber><date>2017-02-28 11:41:17</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>65</revnumber><date>2017-02-28 11:41:06</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>64</revnumber><date>2016-11-22 15:52:34</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>63</revnumber><date>2016-11-22 15:51:58</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>62</revnumber><date>2016-11-22 15:51:44</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>61</revnumber><date>2016-11-22 15:51:24</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>60</revnumber><date>2016-11-22 15:50:45</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>59</revnumber><date>2016-11-22 15:50:29</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>58</revnumber><date>2016-11-22 15:50:21</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>57</revnumber><date>2016-11-22 15:50:05</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>56</revnumber><date>2016-11-22 15:49:25</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>55</revnumber><date>2016-11-22 15:48:44</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>54</revnumber><date>2016-11-22 15:48:26</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>53</revnumber><date>2016-11-22 15:48:16</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>52</revnumber><date>2016-11-22 15:48:09</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>51</revnumber><date>2016-11-22 15:48:00</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>50</revnumber><date>2016-11-22 15:47:47</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>49</revnumber><date>2016-11-21 13:36:04</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>48</revnumber><date>2016-11-21 11:36:21</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>47</revnumber><date>2016-11-21 11:35:58</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>46</revnumber><date>2016-11-21 11:35:45</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>45</revnumber><date>2016-11-21 11:35:25</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>44</revnumber><date>2016-11-21 11:34:23</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>43</revnumber><date>2016-11-21 11:33:51</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>42</revnumber><date>2016-11-21 11:33:23</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>41</revnumber><date>2016-11-21 11:33:02</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>40</revnumber><date>2016-11-21 11:32:15</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>39</revnumber><date>2016-11-21 11:30:54</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>38</revnumber><date>2016-11-21 11:30:37</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>37</revnumber><date>2016-11-21 11:30:12</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>36</revnumber><date>2016-11-21 11:27:41</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>35</revnumber><date>2016-11-21 11:27:09</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>34</revnumber><date>2016-11-18 12:25:45</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>33</revnumber><date>2016-11-18 12:23:39</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>32</revnumber><date>2016-11-17 18:23:59</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>31</revnumber><date>2015-03-20 08:15:37</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>30</revnumber><date>2015-03-19 10:42:02</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>29</revnumber><date>2015-03-18 19:26:39</date><authorinitials>MateuszKopec</authorinitials></revision><revision><revnumber>28</revnumber><date>2015-03-18 18:39:30</date><authorinitials>MateuszKopec</authorinitials></revision><revision><revnumber>27</revnumber><date>2015-03-18 18:19:24</date><authorinitials>MateuszKopec</authorinitials></revision><revision><revnumber>26</revnumber><date>2015-03-18 18:18:51</date><authorinitials>MateuszKopec</authorinitials></revision><revision><revnumber>25</revnumber><date>2015-03-06 14:10:00</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>24</revnumber><date>2015-03-06 14:09:18</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>23</revnumber><date>2015-03-06 14:08:38</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>22</revnumber><date>2015-03-06 14:07:26</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>21</revnumber><date>2015-03-06 14:06:28</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>20</revnumber><date>2015-03-06 14:05:46</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>19</revnumber><date>2015-03-06 14:02:39</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>18</revnumber><date>2015-03-06 14:01:37</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>17</revnumber><date>2014-09-02 16:59:05</date><authorinitials>MichalLenart</authorinitials></revision><revision><revnumber>16</revnumber><date>2014-09-02 16:56:36</date><authorinitials>MichalLenart</authorinitials></revision><revision><revnumber>15</revnumber><date>2014-09-02 16:54:56</date><authorinitials>MichalLenart</authorinitials></revision><revision><revnumber>14</revnumber><date>2014-05-12 15:54:15</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>13</revnumber><date>2014-05-12 15:53:28</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>12</revnumber><date>2014-03-21 19:37:11</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>11</revnumber><date>2014-03-21 19:36:00</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>10</revnumber><date>2013-11-13 10:49:21</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>9</revnumber><date>2012-08-16 11:32:59</date><authorinitials>MichalLenart</authorinitials></revision><revision><revnumber>8</revnumber><date>2012-08-16 11:29:32</date><authorinitials>MichalLenart</authorinitials></revision><revision><revnumber>7</revnumber><date>2012-05-29 13:30:55</date><authorinitials>MichalLenart</authorinitials></revision><revision><revnumber>6</revnumber><date>2012-03-23 22:14:38</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>5</revnumber><date>2011-12-08 13:01:35</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>4</revnumber><date>2011-10-26 12:21:42</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>3</revnumber><date>2011-10-26 12:18:31</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>2</revnumber><date>2011-10-26 12:17:37</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision><revision><revnumber>1</revnumber><date>2011-10-24 01:11:18</date><authorinitials>MaciejOgrodniczuk</authorinitials></revision></revhistory></articleinfo><section><title>The Polish Sejm Corpus / Polski Korpus Sejmowy</title><para>The Polish Sejm Corpus (PSC) is a large (300M-segment) collection of documents (stenographic transcripts, interpellations and questions) of <ulink url="http://www.sejm.gov.pl/english.html">Polish Sejm</ulink> sittings from 1-8 terms of office. </para><para>The first edition of the PSC was prepared in October 2011 and was co-funded by project <ulink url="http://clip.ipipan.waw.pl/CESAR">CESAR</ulink>. The update of the resource with newer data was co-funded by <ulink url="http://clip.ipipan.waw.pl/PSC/CLARIN-PL-2#">CLARIN-PL</ulink> infrastructure.  </para><para>The Sejm Corpus was recently included in the <ulink url="http://clip.ipipan.waw.pl/PPC">Polish Parliamentary Corpus</ulink>. </para><section><title>Corpus data</title><para>The corpus contain transcripts of Sejm sessions saved in TEI P5 format compatible with the annotation used by the <ulink url="http://nkjp.pl/index.php?page=0&amp;lang=1">National Corpus of Polish</ulink>. The resource contains automatically created annotation of: </para><itemizedlist><listitem><para>utterance-level segmentation, </para></listitem><listitem><para>tokenization,  </para></listitem><listitem><para>lemmatization,  </para></listitem><listitem><para>disambiguated morphosyntactic description, </para></listitem><listitem><para>syntactic words, </para></listitem><listitem><para>syntactic groups, </para></listitem><listitem><para>named entities. </para></listitem></itemizedlist><section><title>Single package</title><itemizedlist><listitem><para>Interpellations and questions terms 3-8, sittings terms 1-8, 37.2 GB </para></listitem></itemizedlist></section><section><title>Divided by term and document type</title><informaltable><tgroup cols="5"><colspec colname="col_0" colwidth="0.5*"/><colspec colname="col_1" colwidth="3*"/><colspec colname="col_2" colwidth="5*"/><colspec colname="col_3" colwidth="5*"/><colspec colname="col_4" colwidth="20*"/><tbody><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para><emphasis role="strong">Term</emphasis> </para></entry><entry colsep="1" rowsep="1"><para><emphasis role="strong">Years</emphasis> </para></entry><entry colsep="1" rowsep="1"><para><emphasis role="strong">Sittings</emphasis> </para></entry><entry colsep="1" rowsep="1"><para><emphasis role="strong">Interpellations and questions</emphasis></para></entry><entry colsep="1" rowsep="1"/></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 1    </para></entry><entry colsep="1" rowsep="1"><para> 1991–93   </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad1.tar">1.0 GB</ulink> </para></entry><entry colsep="1" rowsep="1"/></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 2    </para></entry><entry colsep="1" rowsep="1"><para> 1993–97   </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad2.tar">2.6 GB</ulink> </para></entry><entry colsep="1" rowsep="1"/></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 3    </para></entry><entry colsep="1" rowsep="1"><para> 1997–2001 </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad3.tar">2.9 GB</ulink> </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Interpelacje-kad3.tar">1.7 GB</ulink> </para></entry></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 4    </para></entry><entry colsep="1" rowsep="1"><para> 2001–05   </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad4.tar">3.4 GB</ulink> </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Interpelacje-kad4.tar">2.4 GB</ulink> </para></entry></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 5    </para></entry><entry colsep="1" rowsep="1"><para> 2005–07   </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad5.tar">1.4 GB</ulink> </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Interpelacje-kad5.tar">2.0 GB</ulink> </para></entry></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 6    </para></entry><entry colsep="1" rowsep="1"><para> 2007–11   </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad6.tar">3.2 GB</ulink> </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Interpelacje-kad6.tar">4.8 GB</ulink> </para></entry></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 7    </para></entry><entry colsep="1" rowsep="1"><para> 2011–15   </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Posiedzenia-kad7.tar">2.7 GB</ulink> </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Interpelacje-kad7.tar">8.0 GB</ulink> </para></entry></row><row rowsep="1"><entry align="center" colsep="1" rowsep="1"><para> 8    </para></entry><entry colsep="1" rowsep="1"><para> 2015–     </para></entry><entry colsep="1" rowsep="1"><para> 0.7 GB </para></entry><entry colsep="1" rowsep="1"><para> <ulink url="http://sejm.nlp.ipipan.waw.pl/static/PSC-Interpelacje-kad8.tar">1.1 GB</ulink> </para></entry></row></tbody></tgroup></informaltable></section></section><section><title>Publications</title></section><section><title>Searching the corpus</title><para>Online search of the corpus (including Senate data) is available at <ulink url="http://sejm.nlp.ipipan.waw.pl/"/>. </para></section></section></article>