Search Result Optimization. Stand out to surprise customers.Search

Machines now read your text before any person does.

Eight topics about the processing that decides what your sentences are taken to mean, and what that costs when the reading is wrong.

On this page

What it is
Computational linguistics is the machinery that turns language into something a system can compute.
The problem until now
Words on a page were treated as keywords, so the meaning a machine extracts stayed out of view.
What you can do from here
You can write sentences a parser, an extractor and a model can use without changing what you mean.
Computational linguistics: a sentence is parsed into structure, structure yields facts, facts link to entities
Computational linguistics: How the parts depend on each other.
Contents 3

Try this first

Three tests, about ten minutes. They show what a machine extracts from your sentences.

Tests on this page you have run: 0 of 3. The count stays in this browser only.

Test: Computational linguistics

  1. Take one paragraph of your page and write its facts as subject, relation, value.
  2. Put it aside for a moment.
  3. Think: how many did you have to guess?

Facts a machine can pull out, beside facts hidden in style.

Test

  1. Read the first word of every paragraph on your page.
  2. Put it aside for a moment.
  3. Think: how many begin with it, they or this?

Passages that lose their subject when lifted out.

Test

  1. Search your company name together with your city on Google.
  2. Note what you got, before you open anything else.
  3. Think: did a different company appear under the same name?

Whether a system can tell you from a namesake.

Semantic search needs more than semantic splitters. What a system extracts from your page is what your page said, as far as anyone downstream is concerned.

Topics in this field

Extractive summarizationThe summary is now the article for most of the audience.Keyphrase extractionIf your real subject is named once, it is not your subject as far as the system is concerned.Semantic searchThe engine got better at knowing what you meant.Named entity recognitionBeing an entity is a prerequisite for being understood.Topic modelingWhat a topic model can show about a collection of texts, and where its silence begins.Question answeringA confident single answer is the format.Word sense disambiguationYour page competes in whichever meaning the system assigned to it.Sentiment analysisA dashboard of positive and negative tells you the weather, not the cause.

These pages state what each technique does and what follows from it for the person who wrote the text.

A dependency parse tree of one sentence about programmatic SEO
One sentence, taken apart by a parser. This is the level at which your text is actually read.

The other fields

Everything in this field, on one screen

Each point is a page of computational linguistics. Drag, zoom, and click a point to open that page. The whole site is drawn on the knowledge graph.

Computational linguistics

See this field inside the whole site →