{% extends "nopaque.html.j2" %} {% set headline = 'Natural Language Processing' %} {% block page_content %}
{% include 'services/roadmap.html.j2' %}
layersTokenization

Your text is split up into sentences and words, so called tokens, which can then be analyzed.

layersLemmatization

All inflected forms of a word are grouped together so that it can be analyzed as a single item.

layersPart-of-speech Tagging

In accordance with its definition and context, each word is marked up as corresponding to a particular part of speech.

layersNamed-Entity Recognition

Named entities are located and classified into specific categories like persons or locations.

Submit a job

{{ add_job_form.hidden_tag() }}
{{ M.render_field(add_job_form.title, data_length='32', material_icon='title') }}
{{ M.render_field(add_job_form.description, data_length='255', material_icon='description') }}
{{ M.render_field(add_job_form.files, accept='text/plain') }}
{{ M.render_field(add_job_form.language, material_icon='language') }}
{{ M.render_field(add_job_form.version, material_icon='apps') }}
Preprocessing

{{ add_job_form.check_encoding.label.text }}

If the input files are not created with the nopaque OCR service or you do not know if your text files are UTF-8 encoded, check this switch. We will try to automatically determine the right encoding for your texts to process them.

{{ M.render_field(add_job_form.submit, material_icon='send') }}
{% endblock %}