CourseNatural Language Processing: The Complete Course · Module 3: Linguistic Structure: Tags, Parses and Entities · part 22 of 73
Part 22 · Module 3: Linguistic Structure: Tags, Parses and Entities

Lesson 3: Finding products, dates and order numbers in messages

55 min read·14 Oct 2026
Module 3 · Lesson 3 · About 45 minutes · Needs: basic Python; Lesson 1 of this module (the spaCy pipeline) helps but is not required

The situation

It is Monday 21 September 2026, project week 3. Dev, the workshop lead, retypes the same four things from every booking: which product, which service, what date and what price. He asks whether the inbox can underline them for him.

The message he forwards first is HT19, one of Ines's hand-written test messages: "Is the Full Service still £129? If so I'll book it for the 2nd of September." This lesson finds its three entities (simulated data), first with a model trained on news, then with rules and a model working together, and scores every step on the same 40 English test messages.

HT19, FORWARDED BY DEV Is the Full Service still £129 ? If so I'll book it for the 2nd of September . product price date three things Dev retypes from every booking
Dev wants three spans in each booking picked out for him: the product, the price and the date (colours mark the three kinds of entity, not right or wrong).

The rest of this part opens with an account

Signing up is free and takes one email. Nothing to pay, and nothing renews.