# Natural Language Processing

**URL:** <https://discourse.numenta.org/t/natural-language-processing/2667>\
**Category:** Lounge\
**Created:** [August 10, 2017, 3:12pm UTC](https://discourse.numenta.org/t/natural-language-processing/2667 "2017-08-10T15:12:47Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![marty1885](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/marty1885/32/1891_2.png) [@marty1885](https://discourse.numenta.org/u/marty1885)\
**Post date:** [December 15, 2018, 2:52pm UTC](https://discourse.numenta.org/t/natural-language-processing/2667/3 "2018-12-15T14:52:54Z")

</div>

I know this is an old post. But heck.  
I have done a character level sentence generator for [Esperanto](https://en.wikipedia.org/wiki/Esperanto) in HTM. See: [Esperanto NLP using HTM and my findings](https://discourse.numenta.org/t/esperanto-nlp-using-htm-and-my-findings/4289)

When asking HTM to generate sentences. HTM demonstrates that with a single layer of TM. It can learn a sub part of the Esperanto. Namely all words are commonly ended with `-o`, `-as`, `-is`, -`n`, etc… (These endings has grammatical meanings in Esperanto) but not the grammar of the entire sentence; such as the `-n` suffix indicates the object is being acted on.

I’m working on using the hierarchical part of HTM to improve the performance. Hopefully I can come up with better results.

---

_[View the full topic](https://discourse.numenta.org/t/natural-language-processing/2667)._