diff --git a/data/xml/2020.acl.xml b/data/xml/2020.acl.xml
index 2cde863a38..5eacc2812f 100644
--- a/data/xml/2020.acl.xml
+++ b/data/xml/2020.acl.xml
@@ -2496,6 +2496,7 @@
       <doi>10.18653/v1/2020.acl-main.169</doi>
       <video href="http://slideslive.com/38929267"/>
       <bibkey>madaan-etal-2020-politeness</bibkey>
+      <pwccode url="https://github.com/tag-and-generate/Politeness-Transfer-A-Tag-and-Generate-Approach" additional="true">tag-and-generate/Politeness-Transfer-A-Tag-and-Generate-Approach</pwccode>
     </paper>
     <paper id="170">
       <title><fixed-case>BPE</fixed-case>-Dropout: Simple and Effective Subword Regularization</title>
diff --git a/data/xml/2020.coling.xml b/data/xml/2020.coling.xml
index b82a7e044e..00157c5592 100644
--- a/data/xml/2020.coling.xml
+++ b/data/xml/2020.coling.xml
@@ -8167,6 +8167,7 @@
       <url hash="57a55044">2020.coling-demos.2</url>
       <doi>10.18653/v1/2020.coling-demos.2</doi>
       <bibkey>akhbardeh-etal-2020-maintnet</bibkey>
+      <pwcdataset url="https://paperswithcode.com/dataset/10000-people-human-pose-recognition-data">10,000 People - Human Pose Recognition Data</pwcdataset>
     </paper>
     <paper id="3">
       <title><fixed-case>DART</fixed-case>: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool</title>
diff --git a/data/xml/2020.emnlp.xml b/data/xml/2020.emnlp.xml
index fe09c0df81..edd1dae00f 100644
--- a/data/xml/2020.emnlp.xml
+++ b/data/xml/2020.emnlp.xml
@@ -6088,6 +6088,7 @@
       <doi>10.18653/v1/2020.emnlp-main.406</doi>
       <video href="https://slideslive.com/38939315"/>
       <bibkey>gao-gormley-2020-training</bibkey>
+      <pwcdataset url="https://paperswithcode.com/dataset/conll-2003">CoNLL-2003</pwcdataset>
     </paper>
     <paper id="407">
       <title>Multilevel Text Alignment with Cross-Document Attention</title>
diff --git a/data/xml/2021.acl.xml b/data/xml/2021.acl.xml
index 6d029c1a2c..09460771be 100644
--- a/data/xml/2021.acl.xml
+++ b/data/xml/2021.acl.xml
@@ -9168,7 +9168,7 @@
       <award>Outstanding Paper</award>
       <doi>10.18653/v1/2021.acl-long.568</doi>
       <bibkey>aghajanyan-etal-2021-intrinsic</bibkey>
-      <pwccode url="https://github.com/rabeehk/compacter" additional="false">rabeehk/compacter</pwccode>
+      <pwccode url="https://github.com/rabeehk/compacter" additional="true">rabeehk/compacter</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/anli">ANLI</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/glue">GLUE</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/mrpc">MRPC</pwcdataset>
diff --git a/data/xml/2021.emnlp.xml b/data/xml/2021.emnlp.xml
index 97075299ff..e11d071b56 100644
--- a/data/xml/2021.emnlp.xml
+++ b/data/xml/2021.emnlp.xml
@@ -7500,6 +7500,7 @@
       <bibkey>liu-etal-2021-effective</bibkey>
       <doi>10.18653/v1/2021.emnlp-main.481</doi>
       <video href="2021.emnlp-main.481.mp4"/>
+      <pwcdataset url="https://paperswithcode.com/dataset/mimic-iii">MIMIC-III</pwcdataset>
     </paper>
     <paper id="482">
       <title>Contrastive Code Representation Learning</title>
diff --git a/data/xml/2021.naacl.xml b/data/xml/2021.naacl.xml
index 7843555a3b..00f29ba602 100644
--- a/data/xml/2021.naacl.xml
+++ b/data/xml/2021.naacl.xml
@@ -1194,7 +1194,7 @@
       <doi>10.18653/v1/2021.naacl-main.77</doi>
       <bibkey>sun-etal-2021-lightningdot</bibkey>
       <video href="2021.naacl-main.77.mp4"/>
-      <pwccode url="https://github.com/intersun/LightningDOT" additional="false">intersun/LightningDOT</pwccode>
+      <pwccode url="https://github.com/intersun/LightningDOT" additional="true">intersun/LightningDOT</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/coco">COCO</pwcdataset>
     </paper>
     <paper id="78">
@@ -4168,6 +4168,7 @@
       <bibkey>iida-etal-2021-tabbie</bibkey>
       <video href="2021.naacl-main.270.mp4"/>
       <pwccode url="https://github.com/SFIG611/tabbie" additional="false">SFIG611/tabbie</pwccode>
+      <pwcdataset url="https://paperswithcode.com/dataset/viznet-sato">VizNet-Sato</pwcdataset>
     </paper>
     <paper id="271">
       <title>Better Feature Integration for Named Entity Recognition</title>
diff --git a/data/xml/2022.acl.xml b/data/xml/2022.acl.xml
index 0d7b606a62..d7e3af9019 100644
--- a/data/xml/2022.acl.xml
+++ b/data/xml/2022.acl.xml
@@ -6536,6 +6536,7 @@ in the Case of Unambiguous Gender</title>
       <pwcdataset url="https://paperswithcode.com/dataset/csqa">CSQA</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/complexwebquestions">ComplexWebQuestions</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/metaqa">MetaQA</pwcdataset>
+      <pwcdataset url="https://paperswithcode.com/dataset/simplequestions">SimpleQuestions</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/webquestions">WebQuestions</pwcdataset>
     </paper>
     <paper id="423">
@@ -7692,6 +7693,9 @@ in the Case of Unambiguous Gender</title>
       <attachment type="software" hash="df7af561">2022.acl-long.498.software.zip</attachment>
       <bibkey>zhou-etal-2022-distantly</bibkey>
       <doi>10.18653/v1/2022.acl-long.498</doi>
+      <pwccode url="https://github.com/kangISU/Conf-MPU-DS-NER" additional="false">kangISU/Conf-MPU-DS-NER</pwccode>
+      <pwcdataset url="https://paperswithcode.com/dataset/bc5cdr">BC5CDR</pwcdataset>
+      <pwcdataset url="https://paperswithcode.com/dataset/conll-2003">CoNLL-2003</pwcdataset>
     </paper>
     <paper id="499">
       <title><fixed-case>U</fixed-case>ni<fixed-case>X</fixed-case>coder: Unified Cross-Modal Pre-training for Code Representation</title>
diff --git a/data/xml/2022.fl4nlp.xml b/data/xml/2022.fl4nlp.xml
index d97c343de1..9a8168d6be 100644
--- a/data/xml/2022.fl4nlp.xml
+++ b/data/xml/2022.fl4nlp.xml
@@ -50,7 +50,6 @@
       <url hash="ba10ba8f">2022.fl4nlp-1.2</url>
       <bibkey>ro-etal-2022-scaling</bibkey>
       <doi>10.18653/v1/2022.fl4nlp-1.2</doi>
-      <pwcdataset url="https://paperswithcode.com/dataset/billion-word-benchmark">Billion Word Benchmark</pwcdataset>
     </paper>
     <paper id="3">
       <title>Adaptive Differential Privacy for Language Model Training</title>
diff --git a/data/xml/D14.xml b/data/xml/D14.xml
index d06aa1554a..3400c0fbe6 100644
--- a/data/xml/D14.xml
+++ b/data/xml/D14.xml
@@ -1716,6 +1716,7 @@
       <url hash="ccc02ed3">D14-1162</url>
       <doi>10.3115/v1/D14-1162</doi>
       <bibkey>pennington-etal-2014-glove</bibkey>
+      <pwccode url="https://github.com/stanfordnlp/GloVe" additional="true">stanfordnlp/GloVe</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/conll-2003">CoNLL-2003</pwcdataset>
     </paper>
     <paper id="163">
diff --git a/data/xml/D18.xml b/data/xml/D18.xml
index 0c16259cfe..aa468bb36d 100644
--- a/data/xml/D18.xml
+++ b/data/xml/D18.xml
@@ -1515,6 +1515,7 @@
       <bibkey>hayati-etal-2018-retrieval</bibkey>
       <pwccode url="https://github.com/sweetpeach/ReCode" additional="false">sweetpeach/ReCode</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/django">Django</pwcdataset>
+      <pwcdataset url="https://paperswithcode.com/dataset/hearthstone">Hearthstone</pwcdataset>
     </paper>
     <paper id="112">
       <title><fixed-case>SQL</fixed-case>-to-Text Generation with Graph-to-Sequence Model</title>
@@ -2115,6 +2116,7 @@
       <doi>10.18653/v1/D18-1156</doi>
       <bibkey>liu-etal-2018-jointly</bibkey>
       <pwccode url="https://github.com/lx865712528/JMEE" additional="true">lx865712528/JMEE</pwccode>
+      <pwcdataset url="https://paperswithcode.com/dataset/ace-2005">ACE 2005</pwcdataset>
     </paper>
     <paper id="157">
       <title><fixed-case>RESIDE</fixed-case>: Improving Distantly-Supervised Neural Relation Extraction using Side Information</title>
@@ -2635,6 +2637,7 @@
       <bibkey>iyer-etal-2018-mapping</bibkey>
       <pwccode url="https://github.com/sriniiyer/concode" additional="false">sriniiyer/concode</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/concode">CONCODE</pwcdataset>
+      <pwcdataset url="https://paperswithcode.com/dataset/hearthstone">Hearthstone</pwcdataset>
     </paper>
     <paper id="193">
       <title><fixed-case>S</fixed-case>yntax<fixed-case>SQLN</fixed-case>et: Syntax Tree Networks for Complex and Cross-Domain Text-to-<fixed-case>SQL</fixed-case> Task</title>
@@ -7733,6 +7736,7 @@
       <abstract>This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python implementations for subword units. While existing subword segmentation tools assume that the input is pre-tokenized into word sequences, SentencePiece can train subword models directly from raw sentences, which allows us to make a purely end-to-end and language independent system. We perform a validation experiment of NMT on English-Japanese machine translation, and find that it is possible to achieve comparable accuracy to direct subword training from raw sentences. We also compare the performance of subword training and segmentation with various configurations. SentencePiece is available under the Apache 2 license at <url>https://github.com/google/sentencepiece</url>.</abstract>
       <doi>10.18653/v1/D18-2012</doi>
       <bibkey>kudo-richardson-2018-sentencepiece</bibkey>
+      <pwccode url="" additional="true"/>
     </paper>
     <paper id="13">
       <title><fixed-case>C</fixed-case>og<fixed-case>C</fixed-case>omp<fixed-case>T</fixed-case>ime: A Tool for Understanding Time in Natural Language</title>
diff --git a/data/xml/I17.xml b/data/xml/I17.xml
index 6b23e7d944..7edd0b7bd1 100644
--- a/data/xml/I17.xml
+++ b/data/xml/I17.xml
@@ -1755,6 +1755,7 @@
       <bibkey>miceli-barone-sennrich-2017-parallel</bibkey>
       <pwccode url="https://github.com/Avmb/code-docstring-corpus" additional="true">Avmb/code-docstring-corpus</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/django">Django</pwcdataset>
+      <pwcdataset url="https://paperswithcode.com/dataset/hearthstone">Hearthstone</pwcdataset>
     </paper>
     <paper id="54">
       <title>Building Large <fixed-case>C</fixed-case>hinese Corpus for Spoken Dialogue Research in Specific Domains</title>
diff --git a/data/xml/N19.xml b/data/xml/N19.xml
index b543084c11..001e220177 100644
--- a/data/xml/N19.xml
+++ b/data/xml/N19.xml
@@ -1719,6 +1719,7 @@
       <doi>10.18653/v1/N19-1124</doi>
       <video href="https://vimeo.com/360630558"/>
       <bibkey>cai-etal-2019-skeleton</bibkey>
+      <pwccode url="https://github.com/jcyk/skeleton-to-response" additional="false">jcyk/skeleton-to-response</pwccode>
     </paper>
     <paper id="125">
       <title>Jointly Optimizing Diversity and Relevance in Neural Response Generation</title>
@@ -4737,6 +4738,7 @@
       <doi>10.18653/v1/N19-1349</doi>
       <video href="https://vimeo.com/364782035"/>
       <bibkey>ko-etal-2019-linguistically</bibkey>
+      <pwccode url="https://github.com/wjko2/Linguistically-Informed-Specificity-and-Semantic-Plausibility-for-Dialogue-Generation" additional="false">wjko2/Linguistically-Informed-Specificity-and-Semantic-Plausibility-for-Dialogue-Generation</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/cola">CoLA</pwcdataset>
     </paper>
     <paper id="350">
diff --git a/data/xml/P16.xml b/data/xml/P16.xml
index 4b6c14349d..d0df8d6d7e 100644
--- a/data/xml/P16.xml
+++ b/data/xml/P16.xml
@@ -640,6 +640,7 @@
       <doi>10.18653/v1/P16-1057</doi>
       <bibkey>ling-etal-2016-latent</bibkey>
       <pwccode url="https://github.com/deepmind/card2code" additional="true">deepmind/card2code</pwccode>
+      <pwcdataset url="https://paperswithcode.com/dataset/hearthstone">Hearthstone</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/django">Django</pwcdataset>
     </paper>
     <paper id="58">