From 264af6cd17d734efa5cb958f4cded7d852f80237 Mon Sep 17 00:00:00 2001 From: ines Date: Sun, 16 Apr 2017 20:37:29 +0200 Subject: [PATCH] Add documentation --- examples/training/train_new_entity_type.py | 29 ++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/examples/training/train_new_entity_type.py b/examples/training/train_new_entity_type.py index cbe2963d3..ef4070153 100644 --- a/examples/training/train_new_entity_type.py +++ b/examples/training/train_new_entity_type.py @@ -1,3 +1,32 @@ +#!/usr/bin/env python +""" +Example of training and additional entity type + +This script shows how to add a new entity type to an existing pre-trained NER +model. To keep the example short and simple, only four sentences are provided +as examples. In practice, you'll need many more — a few hundred would be a +good start. You will also likely need to mix in examples of other entity +types, which might be obtained by running the entity recognizer over unlabelled +sentences, and adding their annotations to the training set. + +The actual training is performed by looping over the examples, and calling +`nlp.entity.update()`. The `update()` method steps through the words of the +input. At each word, it makes a prediction. It then consults the annotations +provided on the GoldParse instance, to see whether it was right. If it was +wrong, it adjusts its weights so that the correct action will score higher +next time. + +After training your model, you can save it to a directory. We recommend +wrapping models as Python packages, for ease of deployment. + +For more details, see the documentation: +* Training the Named Entity Recognizer: https://spacy.io/docs/usage/train-ner +* Saving and loading models: https://spacy.io/docs/usage/saving-loading + +Developed for: spaCy 1.7.6 +Last tested for: spaCy 1.7.6 +""" +# coding: utf8 from __future__ import unicode_literals, print_function import random