Update metadata from Papers with Code

EricPeter · Sep 1, 2022 · 62614a1 · 62614a1
1 parent 8aeb87a
commit 62614a1
Show file tree

Hide file tree

Showing 12 changed files with 15 additions and 5 deletions.
diff --git a/data/xml/2020.blackboxnlp.xml b/data/xml/2020.blackboxnlp.xml
@@ -141,6 +141,7 @@
       <attachment type="OptionalSupplementaryMaterial" hash="546c8b32">2020.blackboxnlp-1.10.OptionalSupplementaryMaterial.zip</attachment>
       <doi>10.18653/v1/2020.blackboxnlp-1.10</doi>
       <bibkey>treviso-martins-2020-explanation</bibkey>
+      <pwccode url="https://github.com/deep-spin/spec" additional="false">deep-spin/spec</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/e-snli">e-SNLI</pwcdataset>
     </paper>
     <paper id="11">

diff --git a/data/xml/2020.findings.xml b/data/xml/2020.findings.xml
@@ -4458,7 +4458,7 @@
       <url hash="9b74d94c">2020.findings-emnlp.301</url>
       <doi>10.18653/v1/2020.findings-emnlp.301</doi>
       <bibkey>gehman-etal-2020-realtoxicityprompts</bibkey>
-      <pwccode url="" additional="true"/>
+      <pwccode url="https://github.com/allenai/real-toxicity-prompts" additional="false">allenai/real-toxicity-prompts</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/webtext">WebText</pwcdataset>
     </paper>
     <paper id="302">

diff --git a/data/xml/2020.lrec.xml b/data/xml/2020.lrec.xml
@@ -7266,6 +7266,7 @@
       <url hash="c7cb4e23">2020.lrec-1.578</url>
       <language>eng</language>
       <bibkey>amin-nejad-etal-2020-exploring</bibkey>
+      <pwccode url="https://github.com/amin-nejad/mimic-website" additional="true">amin-nejad/mimic-website</pwccode>
     </paper>
     <paper id="579">
       <title>Multi-lingual Mathematical Word Problem Generation using Long Short Term Memory Networks with Enhanced Input Features</title>

diff --git a/data/xml/2020.trac.xml b/data/xml/2020.trac.xml
@@ -163,6 +163,7 @@
       <url hash="75fb6ceb">2020.trac-1.12</url>
       <language>eng</language>
       <bibkey>baruah-etal-2020-aggression</bibkey>
+      <pwcdataset url="https://paperswithcode.com/dataset/urdu-online-reviews">Urdu Online Reviews</pwcdataset>
     </paper>
     <paper id="13">
       <title><fixed-case>L</fixed-case>a<fixed-case>STUS</fixed-case>/<fixed-case>TALN</fixed-case> at <fixed-case>TRAC</fixed-case> - 2020 Trolling, Aggression and Cyberbullying</title>

diff --git a/data/xml/2021.crac.xml b/data/xml/2021.crac.xml
@@ -168,7 +168,7 @@
       <url hash="9cea37bc">2021.crac-1.12</url>
       <bibkey>toshniwal-etal-2021-generalization</bibkey>
       <doi>10.18653/v1/2021.crac-1.12</doi>
-      <pwccode url="https://github.com/shtoshni92/fast-coref" additional="false">shtoshni92/fast-coref</pwccode>
+      <pwccode url="https://github.com/shtoshni92/fast-coref" additional="true">shtoshni92/fast-coref</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/gap-coreference-dataset">GAP Coreference Dataset</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/ontogum">OntoGUM</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/preco">PreCo</pwcdataset>

diff --git a/data/xml/2021.econlp.xml b/data/xml/2021.econlp.xml
@@ -37,7 +37,7 @@
       <url hash="7cc0391b">2021.econlp-1.2</url>
       <bibkey>loukas-etal-2021-edgar</bibkey>
       <doi>10.18653/v1/2021.econlp-1.2</doi>
-      <pwccode url="https://github.com/nlpaueb/edgar-crawler" additional="false">nlpaueb/edgar-crawler</pwccode>
+      <pwccode url="https://github.com/nlpaueb/edgar-crawler" additional="true">nlpaueb/edgar-crawler</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/edgar-corpus">EDGAR-CORPUS</pwcdataset>
     </paper>
     <paper id="3">

diff --git a/data/xml/2021.gwc.xml b/data/xml/2021.gwc.xml
@@ -36,6 +36,8 @@
       <abstract>The results reported in this paper aim to increase the presence of the Uzbek language in the Internet and its usability within IT applications. We describe the initial development of a “word-net” for the Uzbek language compatible to Princeton WordNet. We called it UZWORDNET. In the current version, UZWORDNET contains 28140 synsets, 64389 sense and 20683 words; its estimated accuracy is 75.98%. To the best of our knowledge, it is the largest wordnet for Uzbek existing to date, and the second wordnet developed overall.</abstract>
       <url hash="4567878d">2021.gwc-1.2</url>
       <bibkey>agostini-etal-2021-uzwordnet</bibkey>
+      <pwccode url="https://github.com/LDKR-Group/UzWordnet" additional="false">LDKR-Group/UzWordnet</pwccode>
+      <pwcdataset url="https://paperswithcode.com/dataset/uzwordnet">UzWordnet</pwcdataset>
     </paper>
     <paper id="3">
       <title>Practical Approach on Implementation of <fixed-case>W</fixed-case>ord<fixed-case>N</fixed-case>ets for <fixed-case>S</fixed-case>outh <fixed-case>A</fixed-case>frican Languages</title>

diff --git a/data/xml/2022.acl.xml b/data/xml/2022.acl.xml
@@ -5877,6 +5877,7 @@ in the Case of Unambiguous Gender</title>
       <url hash="45832c10">2022.acl-long.379</url>
       <bibkey>falk-lapesa-2022-reports</bibkey>
       <doi>10.18653/v1/2022.acl-long.379</doi>
+      <pwccode url="https://github.com/blubberli/storytestimony" additional="false">blubberli/storytestimony</pwccode>
     </paper>
     <paper id="380">
       <title>Non-neural Models Matter: a Re-evaluation of Neural Referring Expression Generation Systems</title>

diff --git a/data/xml/2022.findings.xml b/data/xml/2022.findings.xml
@@ -5640,7 +5640,7 @@
       <url hash="769bc50a">2022.findings-naacl.47</url>
       <bibkey>nadejde-etal-2022-cocoa</bibkey>
       <doi>10.18653/v1/2022.findings-naacl.47</doi>
-      <pwccode url="https://github.com/awslabs/sockeye" additional="true">awslabs/sockeye</pwccode>
+      <pwccode url="https://github.com/awslabs/sockeye" additional="false">awslabs/sockeye</pwccode>
     </paper>
     <paper id="48">
       <title><fixed-case>CLEAR</fixed-case>: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations</title>
@@ -6348,6 +6348,7 @@
       <url hash="521cef94">2022.findings-naacl.92</url>
       <bibkey>gao-etal-2022-retrieval</bibkey>
       <doi>10.18653/v1/2022.findings-naacl.92</doi>
+      <pwccode url="https://github.com/yifan-gao/multilingual_keyphrase_generation" additional="false">yifan-gao/multilingual_keyphrase_generation</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/kp20k">KP20k</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/microsoft-academic-graph">Microsoft Academic Graph</pwcdataset>
     </paper>

diff --git a/data/xml/2022.naacl.xml b/data/xml/2022.naacl.xml
@@ -855,6 +855,7 @@
       <url hash="af15dc46">2022.naacl-main.57</url>
       <bibkey>lu-etal-2022-neurologic</bibkey>
       <doi>10.18653/v1/2022.naacl-main.57</doi>
+      <pwccode url="https://github.com/GXimingLu/a_star_neurologic" additional="false">GXimingLu/a_star_neurologic</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/commongen">CommonGen</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/rocstories">ROCStories</pwcdataset>
     </paper>
@@ -7822,7 +7823,7 @@
       <url hash="e74f6131">2022.naacl-industry.24</url>
       <bibkey>ayoola-etal-2022-refined</bibkey>
       <doi>10.18653/v1/2022.naacl-industry.24</doi>
-      <pwccode url="https://github.com/alexa/refined" additional="true">alexa/refined</pwccode>
+      <pwccode url="https://github.com/amazon-research/ReFinED" additional="true">amazon-research/ReFinED</pwccode>
       <pwcdataset url="https://paperswithcode.com/dataset/ace-2004">ACE 2004</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/aida-conll-yago">AIDA CoNLL-YAGO</pwcdataset>
       <pwcdataset url="https://paperswithcode.com/dataset/aquaint">AQUAINT</pwcdataset>

diff --git a/data/xml/W16.xml b/data/xml/W16.xml
@@ -6556,6 +6556,7 @@
       <url hash="db735aa0">W16-3210</url>
       <doi>10.18653/v1/W16-3210</doi>
       <bibkey>elliott-etal-2016-multi30k</bibkey>
+      <pwccode url="" additional="true"/>
       <pwcdataset url="https://paperswithcode.com/dataset/flickr30k">Flickr30k</pwcdataset>
     </paper>
     <paper id="11">

diff --git a/data/xml/W18.xml b/data/xml/W18.xml
@@ -7316,6 +7316,7 @@
       <abstract>This paper describes our participation in the First Shared Task on Aggression Identification. The method proposed relies on machine learning to identify social media texts which contain aggression. The main features employed by our method are information extracted from word embeddings and the output of a sentiment analyser. Several machine learning methods and different combinations of features were tried. The official submissions used Support Vector Machines and Random Forests. The official evaluation showed that for texts similar to the ones in the training dataset Random Forests work best, whilst for texts which are different SVMs are a better choice. The evaluation also showed that despite its simplicity the method performs well when compared with more elaborated methods.</abstract>
       <bibkey>orasan-2018-aggressive</bibkey>
       <pwccode url="https://github.com/dinel/aggression_identification" additional="false">dinel/aggression_identification</pwccode>
+      <pwcdataset url="https://paperswithcode.com/dataset/200-people-chinese-speech-data-by-mobile">200 People-Chinese Speech Data by Mobile Phone</pwcdataset>
     </paper>
     <paper id="15">
       <title>Aggression Detection in Social Media using Deep Neural Networks</title>