Update metadata from Papers with Code

data/xml/2020.semeval.xml

@@ -2401,6 +2401,7 @@
       <url hash="929044de">2020.semeval-1.198</url>
       <bibkey>herath-etal-2020-adelaidecyc</bibkey>
       <doi>10.18653/v1/2020.semeval-1.198</doi>
+      <pwccode url="" additional="true"/>
     </paper>
     <paper id="199">
       <title><fixed-case>ANDES</fixed-case> at <fixed-case>S</fixed-case>em<fixed-case>E</fixed-case>val-2020 Task 12: A Jointly-trained <fixed-case>BERT</fixed-case> Multilingual Model for Offensive Language Detection</title>

data/xml/2021.emnlp.xml

@@ -3180,6 +3180,7 @@
       <bibkey>yang-etal-2021-syntactically</bibkey>
       <doi>10.18653/v1/2021.emnlp-main.203</doi>
       <video href="2021.emnlp-main.203.mp4"/>
+      <pwccode url="https://github.com/lanse-sir/sup" additional="false">lanse-sir/sup</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/sst">SST</pwcdataset>
     </paper>
     <paper id="204">

data/xml/2022.wnut.xml

@@ -259,7 +259,6 @@
       <abstract>The automatic categorization of support tickets is a fundamental tool for modern businesses. Such requests are most commonly composed of concise textual descriptions that are noisy and filled with technical jargon. In this paper, we test the effectiveness of pre-trained LMs for the classification of issues related to software bugs. First, we test several strategies to produce single, ticket-wise representations starting from their BERT-generated word embeddings. Then, we showcase a simple yet effective way to build a multi-level classifier for the categorization of documents with two hierarchically dependent labels. We experiment on a public bugs dataset and compare our results with standard BERT-based and traditional SVM classifiers. Our findings suggest that both embedding strategies and hierarchical label dependencies considerably impact classification accuracy.</abstract>
       <url hash="afd09a7c">2022.wnut-1.22</url>
       <bibkey>marcuzzo-etal-2022-multi</bibkey>
-      <pwccode url="https://gitlab.com/distration/dsi-nlp-publib" additional="false">distration/dsi-nlp-publib</pwccode>
     </paper>
     <paper id="23">
       <title>Towards better structured and less noisy Web data: Oscar with Register annotations</title>

data/xml/P19.xml

@@ -1039,14 +1039,8 @@
       <url hash="a6b4f482">P19-1075</url>
       <doi>10.18653/v1/P19-1075</doi>
       <bibkey>zheng-etal-2019-chid</bibkey>
-      <pwccode url="https://github.com/zhengcj1/ChID-Dataset" additional="true">zhengcj1/ChID-Dataset</pwccode>
+      <pwccode url="https://github.com/chujiezheng/ChID-Dataset" additional="false">chujiezheng/ChID-Dataset</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/chid">ChID</pwcdataset>
-      <pwcdataset url="https://paperswithcode.com/dataset/cbt">CBT</pwcdataset>
-      <pwcdataset url="https://paperswithcode.com/dataset/cloth">CLOTH</pwcdataset>
-      <pwcdataset url="https://paperswithcode.com/dataset/cmrc-2017">CMRC 2017</pwcdataset>
-      <pwcdataset url="https://paperswithcode.com/dataset/children-s-book-test">Children's Book Test</pwcdataset>
-      <pwcdataset url="https://paperswithcode.com/dataset/lambada">LAMBADA</pwcdataset>
-      <pwcdataset url="https://paperswithcode.com/dataset/who-did-what">Who-did-What</pwcdataset>
     </paper>
     <paper id="76">
       <title>Automatic Evaluation of Local Topic Quality</title>

data/xml/Q18.xml

@@ -313,6 +313,7 @@
       <url hash="62868a98">Q18-1023</url>
       <video href="https://vimeo.com/285804931"/>
       <bibkey>kocisky-etal-2018-narrativeqa</bibkey>
+      <pwccode url="" additional="true"/>
       <pwcdataset url="https://paperswithcode.com/dataset/narrativeqa">NarrativeQA</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/booktest">BookTest</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/cbt">CBT</pwcdataset>

data/xml/W14.xml

@@ -4243,6 +4243,7 @@
       <url hash="1225d80d">W14-2608</url>
       <doi>10.3115/v1/W14-2608</doi>
       <bibkey>buschmeier-etal-2014-impact</bibkey>
+      <pwccode url="https://github.com/kbuschme/irony-detection" additional="false">kbuschme/irony-detection</pwccode>
     </paper>
     <paper id="9">
       <title>Modelling Sarcasm in <fixed-case>T</fixed-case>witter, a Novel Approach</title>

data/xml/W19.xml

@@ -14136,7 +14136,6 @@ One of the references was wrong therefore it is corrected to cite the appropriat
       <url hash="9b228715">W19-5945</url>
       <doi>10.18653/v1/W19-5945</doi>
       <bibkey>keizer-etal-2019-user</bibkey>
-      <pwccode url="https://bitbucket.org/skeizer/madrigal" additional="false">skeizer/madrigal</pwccode>
     </paper>
     <paper id="46">
       <title>Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response</title>