# Semantic Search using ML capabilities

**URL:** <https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860>\
**Category:** Elasticsearch\
**Created:** [July 28, 2020, 8:15am UTC](https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860 "2020-07-28T08:15:02Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Shubham\_Mittal](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/shubham_mittal/32/55002_2.png) [@Shubham\_Mittal](https://discuss.elastic.co/u/Shubham_Mittal)\
**Post date:** [July 28, 2020, 8:15am UTC](https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860/1 "2020-07-28T08:15:02Z")

</div>

Hi Team,

Could you please tell if elastic search currently supports semantic search using machine learning features?

---

<div class="post-metadata">

**Author:** ![Mark\_Harwood](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/mark_harwood/32/10538_2.png) [@Mark\_Harwood](https://discuss.elastic.co/u/Mark_Harwood)\
**Post date:** [July 28, 2020, 9:12am UTC](https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860/2 "2020-07-28T09:12:13Z")

</div>

You can use [significant\_text](https://www.youtube.com/watch?v=zH7bizwjj20) to identify terms or phrases related to your search. Your client app could allow users to cherry-pick from suggestions or you could automatically add the best suggestions to expand a query.

---

<div class="post-metadata">

**Author:** ![Shubham\_Mittal](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/shubham_mittal/32/55002_2.png) [@Shubham\_Mittal](https://discuss.elastic.co/u/Shubham_Mittal)\
**Post date:** [July 28, 2020, 9:44pm UTC](https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860/3 "2020-07-28T21:44:33Z")

</div>

Is Elastic search Graph or any listed features of enterprise elasticsearch capable to provide such ontologies and taxonomies based search?

---

<div class="post-metadata">

**Author:** ![Mark\_Harwood](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/mark_harwood/32/10538_2.png) [@Mark\_Harwood](https://discuss.elastic.co/u/Mark_Harwood)\
**Post date:** [July 28, 2020, 10:19pm UTC](https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860/4 "2020-07-28T22:19:40Z")

</div>

The “annotated\_text” plugin allows you to store and search structured annotations inside text.

[Here](https://youtu.be/_ThbDlhp1AQ) is a demo of a prototype application operating on an index of English Wikipedia articles. The original article text is annotated with entity IDs and type information from the DBPedia ontology. Using content enriched in this way you can search for specific things eg JFK or their type eg president and combine with nearby text eg search for politicians near any mentions of bribery or corruption.

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [August 25, 2020, 10:30pm UTC](https://discuss.elastic.co/t/semantic-search-using-ml-capabilities/242860/5 "2020-08-25T22:30:58Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.