Hacker News Reader

You don't solve the inflexion problem. You would need something where the lemmization tokenization of the sentence is easily accessible to a grammar engine. Something horrible like: <div ><lemm="personnal pronoun">I</lemm> <lemm=verb>have</lemm>< <case=accusative quant=3><lemm=noun quantifier /><lemm=....</div>

View on HN

Lemmatization isn't necessary in this case, as there's no need for a grammar engine.

Here's how we handle pluralization on our backend (all abstracted away from the user): For a language with 2 plural forms (ie. French), we create 2 different phrases. One singular and one plural. Or for languages like Arabic, we create 6 different phrases for each plural form. We then send each plural form of the phrase to a human translator, who translates each phrase independently.

This ensures proper plural forms for all variations, without the need for complicated grammar syntax.

Reply on news.ycombinator.com