was successfully added to your cart.

Improved Rule-Based Annotation in Annotation Lab

Rule-based annotation, introduced in 2.6.0, with limited options, was improved in this release. The Rule creation UI form was simplified and extended, and helpful tips were added to each field.<br aria-hidden=”true” />While creating a rule, the user can define the scope of the rule as being a sentence or document.
<ul type=”disc”>
<li>When <code class=”code_inline”>document</code> is selected, the rule searched for a match on each sentence of a document.</li>
<li>When <code class=”code_inline”>sentence</code> is selected, the rule searched for a match on each token of a sentence.</li>
A new toggle parameter <code class=”code_inline”>Complete Match Regex</code> is added to the rules. <code class=”code_inline”>Complete Match Regex</code> can be toggled on to preannotate the entity that exactly matches the regex or dictionary value regardless of the <code class=”code_inline”>Match Scope</code>.
Users can now view the <code class=”code_inline”>Help Text</code> for all rule fields by hovering over the <code class=”code_inline”>?</code> icon. This release also adds the validation of fields: Suffix, Prefix, and Exception such that only single tokens are accepted.
When clearing prefixes, suffixes, and exceptions from the input field, the operation was not saved. In this version, these fields can be cleared to EMPTY and saved. Also case-sensitive is always true (and hence the toggle is hidden in this case) for REGEX while the case-sensitive toggle for dictionary can be toggled on or off.
<div class=”pb40″>Users can now download the uploaded dictionary of an existing rule. To download the CSV, users need to go to Models Hub &gt; Available Rules, click on the edit button of the required rule, and then click download.</div>
<div class=”pb40″><a class=”fancybox image” href=”https://user-images.githubusercontent.com/33893292/152673187-6503b47e-c5d8-404a-a6a1-ae8d79879016.png” target=”_blank” rel=”noopener noreferrer” data-auth=”NotApplicable” data-linkindex=”0″><img class=” lazyloaded” src=”https://user-images.githubusercontent.com/33893292/152673187-6503b47e-c5d8-404a-a6a1-ae8d79879016.png” alt=”download csv” width=”775″ data-imagetype=”External” data-src=”https://user-images.githubusercontent.com/33893292/152673187-6503b47e-c5d8-404a-a6a1-ae8d79879016.png” /></a></div>

In the previous release, if a dictionary-based rule was defined with an invalid CSV file, the preannotation server would crash and would only recover when the rule was removed from the configuration. This issue has been fixed. Also, it is possible to upload both vertical and horizontal CSV which can consist of multi-token dictionary values.

Horizontal CSV for Disease Rule:
<code class=”code_inline”>disease</code>,<code class=”code_inline”>chickenpox</code>,<code class=”code_inline”>pneumonia</code>,<code class=”code_inline”>common cold</code>,<code class=”code_inline”>tetanus</code>

<br aria-hidden=”true” />Vertical CSV for Disease Rule:

<code class=”code_inline”>disease</code>
<code class=”code_inline”>chickenpox</code>
<code class=”code_inline”>pneumonia</code>
<code class=”code_inline”>common cold</code>
<code class=”code_inline”>tetanus</code>

Note: The first value in the CSV should be the same as the name of the rule.

<a href=”https://medium.com/spark-nlp/contextual-parser-increased-flexibility-extracting-entities-in-spark-nlp-123ed58672f0″>For further details about ContextualParser which drives the Rule-based annotation.</a>


<div class=”pb40″>
<h3>GET &amp; INSTALL IT <a href=”https://www.johnsnowlabs.com/install/”>HERE.</a></h3>
<h3>FULL FEATURE SET <a href=”https://www.johnsnowlabs.com/annotation-lab/”>HERE</a>.</h3>