NER: example in PHP with TransformersPHP

Token classification pipeline with Xenova/bert-base-NER

This example uses the TransformersPHP token-classification pipeline to detect entities in text and output token-to-label pairs.

Example of use


                
<?php

include 'code-en.php';

if ($nerError !== null) {
    echo 'Warning: ' . $nerError . PHP_EOL;
    return;
}

echo $text;
echo PHP_EOL . '-----------' . PHP_EOL;

if ($entities === []) {
    echo 'No entities found.' . PHP_EOL;
    return;
}

foreach ($entities as $entity) {
    echo ($entity['word'] ?? '') . ' -> ' . ($entity['entity'] ?? '') . PHP_EOL;
}

Result: Memory: 0 Mb Time running: < 0.001 sec.


                Microsoft signed a contract with John Smith in London for $3 million.
-----------
Microsoft -> B-ORG
John -> B-PER
Smith -> I-PER
London -> B-LOC