# 3C Shared Task — Data

来源：https://www.kaggle.com/competitions/3c-shared-task-purpose/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>Dataset for 3C Shared Task</h2>
<h3>Train Dataset</h3>
<p>The participants will be provided with a labeled training dataset of 3000 instances annotated using the ACT platform.<p>
                        <p>The dataset is provided in csv format and contains the following fields:<p>
                        <ul>
                            <li>Unique Identifier</li>
  			    <li>COREID of Citing Paper</li>
                            <li>Citing Paper Title</li>
                            <li>Citing Paper Author</li>
                            <li>Cited Paper Title</li>
                            <li>Cited Paper Author</li>
  			    <li>Citation Context</li>
  			    <li>Citation Class Label</li>
  			</ul>
<p>Each ciation context in the dataset contains the label, "#AUTHOR_TAG", which represents the citation that is being considered. The citation class labels corresponds to values between 0 and 5, where each value represents the following categories:

                         <dl>   
                              <dd>0  -  BACKGROUND</dd>
                              <dd>1  -  COMPARES_CONTRASTS</dd>
                              <dd>2  -  EXTENSION</dd>
                              <dd>3  -  FUTURE</dd>
                              <dd>4  -  MOTIVATION</dd>
                              <dd>5  -  USES</dd>
  			 </dl>
</p>

<h3>Test Dataset</h3>
The test dataset, in cvs format, contains 1000 instances, with all fields in the train set, except for the labels.