Word-in-Context Target Sense Verification

Formally, WiC is framed as a binary classification task. Each instance in WiC-TSV consists of a target word w with a corresponding target sense s represented by either its definition (subtask 1) or its hypernym/s (subtask 2), and a context c containing the target word w. The task aims to determine whether the meaning of the word w used in the context c matches the target sense s. In the following table there are some examples from the dataset.

Subtasks

 WiC-TSV has three subtasks - participants can submit results in any of the subtasks:

Subtask 1: Definitions

In Subtask 1 systems make use of definitions for deciding whether the target word in context corresponds to the given definition or not.

Subtask 2: Hypernyms

In Subtask 2 systems make use of hypernymy information for deciding whether the target word in context is a hyponym of the given hypernym or not.

Subtask 3: Definitions + Hypernyms

In subtask 3 systems can make use of both sources of information, i.e., definitions and hypernyms.