# FAA 2020: Cognate Identification — Data

来源：https://www.kaggle.com/competitions/faa-2020-cognate-identification/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>File descriptions</h2>
<ul>
<li><strong>IE2012-lexical-data.train.csv</strong> - the training dataset</li>
<li><strong>IE2013-lexical-data.test.csv</strong> - the test dataset</li>
<li><strong>IE2012-test-maj-baseline.csv</strong> - a sample submission that implements the majority baseline (i.e., the 0 class for all examples)</li>
</ul>

<h2>Data fields</h2>
<ul>
<li><strong>Id</strong> - id unique for pair of words (i.e., the cognate candidates)</li>
<li><strong>Category</strong> - Class label (0 or 1) indicating whether the 2 words are cognates or not, respectively)</li>
<li><strong>word1</strong> - string or phonetic representation of the first word </li>
<li><strong>language1</strong> - language of the first word</li>
<li><strong>word2</strong> - string or phonetic representation of the second word </li>
<li><strong>language2</strong> - language of the second word</li>
<li><strong>meaning</strong> - concept or meaning associated with the two words</li>
<li><strong>Usage</strong> - field to be ignored</li>
</ul>