Word-in-Context Target Sense Verification

<pre>Formally, WiC is framed as a&nbsp;<strong>binary classification</strong>&nbsp;task. Each instance in WiC-TSV consists of a target word&nbsp;<em>w</em>&nbsp;with a corresponding target sense&nbsp;<em>s</em>&nbsp;represented by either its definition (subtask 1) or its hypernym/s (subtask 2), and a context&nbsp;<em>c</em>&nbsp;containing the target word&nbsp;<em>w</em>. The task aims to determine whether the meaning of the word&nbsp;<em>w</em>&nbsp;used in the context&nbsp;<em>c</em>&nbsp;matches the target sense&nbsp;<em>s</em>. In the following table there are some examples from the dataset. </pre> <p>&nbsp;</p> <p>Subtasks</p> <p>&nbsp;WiC-TSV has&nbsp;<strong>three subtasks</strong>&nbsp;- participants can submit results in any of the subtasks:</p> <p>Subtask 1: Definitions</p> <p>In Subtask 1 systems make use of&nbsp;<strong>definitions</strong>&nbsp;for deciding whether the target word in context corresponds to the given definition or not.</p> <p>Subtask 2: Hypernyms</p> <p>In Subtask 2 systems make use of&nbsp;<strong>hypernymy</strong>&nbsp;information for deciding whether the target word in context is a hyponym of the given hypernym or not.</p> <p>Subtask 3: Definitions + Hypernyms</p> <p>In subtask 3 systems can make use of&nbsp;<strong>both</strong>&nbsp;sources of information, i.e., definitions and hypernyms.</p>