Watch a machine-learning system parse the grammatical structure of sentences

So FoxType is just Spacy[0]? I honestly thought this might be something different until I checked out the Spacy page and saw FoxType listed as a customer. Kind of a dick move simply repackaging other people&#x27;s work and passing. It off as your own. (Yes, this is literally just the &quot;displacy&quot; demo.)<p>Spacy is a pretty good system. It&#x27;s fast, way faster thank NLTK and the Stanford stuff and it&#x27;s pretty accurate. Also it&#x27;s licensing is pretty flexible. The only knock I have against it is the lack of bindings for languages other than Python, but whatever.<p>[0] <a href="https:&#x2F;&#x2F;spacy.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;spacy.io&#x2F;</a>

Whilst an impressive demonstration, how is it an example of machine learning? It looks like lexical analysis to me.

Seems to fall for a lot of easy traps. Garden path sentences (&quot;The old man the boats&quot; or &quot;The horse raced past the barn fell&quot;) are parsed wrong, and it parses the two sentences&#x2F;phrases &quot;When he did that I laughed&quot; and &quot;When he said that I laughed&quot; identically - by interpreting &quot;that&quot; as a preposition in both cases, which it isn&#x27;t.<p>It&#x27;s cool that it parses on the fly. But unless it parses <i>correctly</i> I don&#x27;t see how it actually serves a purpose other than just looking cool.

It doesn&#x27;t do well on the classic: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Buffalo_buffalo_Buffalo_buffalo_buffalo_buffalo_Buffalo_buffalo" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Buffalo_buffalo_Buffalo_buffal...</a>

Very interesting demo. I am not being critical, but it does not do anaphora resolution (resolving pronouns to noun phrases, etc).

It got &quot;colorless green ideas sleep furiously,&quot; wrong.

&quot;The cat ate the farty bird&quot;<p>Sorry machine, &quot;farty&quot; is an adjective, not a noun.