# Improving OpenSearch relevance with better normalization (beyond stemming)

**URL:** <https://forum.opensearch.org/t/improving-opensearch-relevance-with-better-normalization-beyond-stemming/27997>\
**Category:** Open Source Elasticsearch and Kibana\
**Created:** [April 19, 2026, 7:29pm UTC](https://forum.opensearch.org/t/improving-opensearch-relevance-with-better-normalization-beyond-stemming/27997 "2026-04-19T19:29:29Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![TonyJ](https://avatars.discourse-cdn.com/v4/letter/t/e9c0ed/32.png) [@TonyJ](https://forum.opensearch.org/u/TonyJ)\
**Post date:** [April 19, 2026, 7:29pm UTC](https://forum.opensearch.org/t/improving-opensearch-relevance-with-better-normalization-beyond-stemming/27997/1 "2026-04-19T19:29:29Z")

</div>

**Versions** (relevant - OpenSearch/Dashboard/Server OS/Browser):

**Describe the issue** :

In several OpenSearch projects we’ve seen stemming introduce noise early in the pipeline, especially in multilingual setups.

For example:

- “organization” → “organ”

- “news” → “new”

- “united” → “unit”

These kinds of transformations collapse unrelated terms into the same form, which affects matching quality and introduces noise into the index.

In practice, this often leads to:

- less precise retrieval

- more reliance on query-side complexity (ngrams, fuzzy, etc.)

- inconsistent behavior across languages

We’ve been exploring an alternative approach using a lightweight plugin that adds proper lemmatization and decompounding before indexing. It’s simple to integrate and doesn’t require changes to query logic.

So far, we’re seeing improvements in:

- lexical matching

- index quality

- consistency (also when combined with semantic search)

More detailed examples here:  
[https://www.linkedin.com/pulse/how-increase-search-relevance-elasticsearch-better-text-tony-chac%C3%B3n-arkic](https://www.linkedin.com/pulse/how-increase-search-relevance-elasticsearch-better-text-tony-chac%C3%B3n-arkic)

Curious how others are handling this kind of issue.

**Configuration** :

1. OpenSearch (standard analyzers with stemming)
2. Multilingual datasets
3. Combination of lexical and semantic search in some cases

**Relevant Logs or Screenshots** :

---

<div class="post-metadata">

**Author:** ![TonyJ](https://avatars.discourse-cdn.com/v4/letter/t/e9c0ed/32.png) [@TonyJ](https://forum.opensearch.org/u/TonyJ)\
**Post date:** [April 20, 2026, 3:02pm UTC](https://forum.opensearch.org/t/improving-opensearch-relevance-with-better-normalization-beyond-stemming/27997/2 "2026-04-20T15:02:22Z")

</div>

One thing we’re seeing is that many teams compensate with ngrams/fuzzy or move to semantic but the normalization layer is still noisy.

Curious if anyone has tried improving normalization before indexing instead?

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex019/uploads/mauve_hedgehog/original/2X/3/33547ea01a5b12dcca2958411d3edd97ae2ea8c1.png) [@system](https://forum.opensearch.org/u/system)\
**Post date:** [June 19, 2026, 3:03pm UTC](https://forum.opensearch.org/t/improving-opensearch-relevance-with-better-normalization-beyond-stemming/27997/3 "2026-06-19T15:03:08Z")

</div>

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.