# Norwegian Nynorsk Stemmer Benchmarks

This page reports same-language stemming benchmarks for Norwegian Nynorsk. Accuracy is listed first because speed without root agreement is not enough to interpret stemmer quality.

All speed values are environment-specific and were measured on the hardware and JVM listed in the [benchmark overview](../index.md). Speed benchmark operations process changed dictionary tokens only. Accuracy uses the complete Radixor dictionary for the language.

Radixor must not be read as simply "slower" when a narrow competitor has a lower timing row. In these tables Radixor is the quality-oriented baseline: its exact-root accuracy is typically close to 100%, while many faster rule-based, light, minimal, or possessive filters reach that speed by doing much less linguistic work and often score far lower in `All exact` and `Changed exact`. The Radixor rows in this benchmark refresh use the contracted compiled patch trie: compilation collapses uniform patch-command subtrees into accepting leaves, reducing hot lookup depth while preserving the preferred stemming result measured by the accuracy pass. The [EnglishRadixorDictionaryCoverageBenchmark](../reference/english-coverage.md) table shows the resulting quality/speed envelope explicitly. The same interpretation applies to this language page: speed rows must be read together with the accuracy table above them.

## Dictionary Corpus

| Model ID | Model version | Language | Dictionary rows | Complete quality tokens | Already-root tokens | Changed speed tokens |
| --- | --- | --- | ---: | ---: | ---: | ---: |
| `nn-no-default` | `1.0.0` | `NN_NO` | 4,688 | 19,651 | 6,089 | 13,562 |

## Radixor Patch Command Distribution

Radixor stores the preferred transformation for each normalized dictionary word form as a compiled patch command. This distribution shows which runtime command class is selected by the trained trie for the complete default-model dictionary. The total number of preferred patch commands analyzed for this language is **19,651**.

| Command class | Meaning | Word forms | Share |
| --- | --- | ---: | ---: |
| `AppendCharacterCommand` | Appends one character to the end of the word form. | 312 | 1.588% |
| `BackwardCompoundCommand` | Applies a multi-step backward patch made from skip, delete, insert, and replace operations. | 1,456 | 7.409% |
| `DeleteSuffixCommand` | Deletes one or more trailing characters from the word form. | 11,325 | 57.631% |
| `PreserveCommand` | Returns the word form unchanged because it already matches the preferred root. | 6,031 | 30.691% |
| `ReplaceLastCharacterCommand` | Replaces the final character of the word form. | 527 | 2.682% |

## Accuracy

Accuracy is computed from JMH auxiliary counters in the current report. The counters are deterministic for a fixed corpus and stemmer; percentages divide matching counters by evaluated counters from the same report and are not timing metrics.

| Stemmer | All exact | Changed exact | Root preserved | Note |
| --- | ---: | ---: | ---: | --- |
| Radixor | 93.089% | 91.395% | 96.863% | Full Radixor dictionary patch-command stemmer. |
| Official Snowball direct | 60.974% | 60.212% | 62.670% | Official Snowball generated Java stemmer; rule-based suffix algorithm. |
| Lucene SnowballFilter | 60.918% | 60.146% | 62.638% | Lucene TokenFilter integration path around the Snowball algorithm. |




## Speed

Speed uses JMH average time, 5 warmup iterations, 10 measurement iterations, 3 independent forks, and 1 thread. Relative factor is computed against the single Radixor row on this language page. Values below 1.000 are faster than that Radixor baseline; values above 1.000 are slower.

| Stemmer | Benchmark method | Score ms/op | Error ms | ns/token | Relative vs Radixor | Note |
| --- | --- | ---: | ---: | ---: | ---: | --- |
| Radixor | `radixor[NORWEGIAN_NYNORSK]` | 0.617 | 0.062 | 45.5 | 1.000 | Full Radixor dictionary patch-command stemmer. |
| Official Snowball direct | `snowballDirect[NORWEGIAN_NYNORSK]` | 0.955 | 0.076 | 70.4 | 1.548 | Official Snowball generated Java stemmer; direct API. |
| Lucene SnowballFilter | `luceneSnowballFilter[NORWEGIAN_NYNORSK]` | 1.352 | 0.106 | 99.7 | 2.191 | Lucene TokenFilter path around Snowball; includes TokenStream overhead. |




## Interpretation Notes

- Radixor is a dictionary-derived patch-command stemmer. Its quality depends on the language resource used to train the compiled trie.
- Light, minimal, plural, and possessive filters are narrow baselines. They can be fast because they intentionally perform less linguistic work.
- Lucene TokenFilter rows include TokenStream, attribute, and required normalization overhead. Direct rows measure exposed direct APIs.
- Morfologik rows are dictionary-based and can emit multiple terms for one input token. Quality rows use the first returned term when no ranking weight is available.
- Snowball rows are rule-based generated suffix stemmers; they are useful algorithmic baselines, not dictionary-root equivalence guarantees.

<!-- STEMMING-QUALITY:START -->

## Stemming Quality

Runtime performance and linguistic grouping quality are independent dimensions. This section evaluates language `NN_NO` using the complete validated stemming-quality result matrix. Every distinct surface form is one evaluated item and can belong to several dictionary groups. Two forms are a positive pair when their group-membership sets intersect and a negative pair when those sets are disjoint. A pair shared through several groups is counted once. Exact equality with a predetermined lemma is not required.

`ALL_WORDS` includes every valid group and its original forms. `LOWERCASE_GROUPS_ONLY` excludes an entire group when any Unicode code point is uppercase or titlecase; retained words are not lowercased or otherwise rewritten. This isolates case-handling effects without changing retained inputs. [Download the complete machine-readable result snapshot](../data/stemming-quality.csv).

### Evaluation Scope and Key Findings

The default model is `nn-no-default`, loaded from classpath resource `org/egothor/stemmer/models/nn-no-default/stemmer.gz`. The following findings compare only deterministic `PRIMARY_OUTPUT` rows over identical included groups; candidate policies are reported separately as capability analyses.

- **ALL_WORDS:** `Radixor` ranks first by balanced accuracy at **0.950991** among 3 deterministic stemmers. The runner-up is `SNOWBALL NORWEGIAN NYNORSK DIRECT` at 0.868094, a difference of 0.082897. This rank does not imply leadership in throughput or every secondary metric.
- **LOWERCASE_GROUPS_ONLY:** `Radixor` ranks first by balanced accuracy at **0.951104** among 3 deterministic stemmers. The runner-up is `SNOWBALL NORWEGIAN NYNORSK DIRECT` at 0.868252, a difference of 0.082852. This rank does not imply leadership in throughput or every secondary metric.
### `ALL_WORDS`

This mode contains **5 result rows**, **3 evaluated stemmers**, and **3 output policies**. Applied-row and form counts are shown per row because adapters share the language corpus but policy rows remain independently auditable. `PRIMARY_OUTPUT` and `ALL_CANDIDATES` rankings are ordered by unrounded balanced accuracy, followed by MCC, F1, over-stemming rate, over-stemming count, under-stemming rate, and stemmer. `ANY_CANDIDATE` has no single rank metric and is listed alphabetically. Balanced accuracy is a navigation metric, not a universally authoritative quality score.

#### `PRIMARY_OUTPUT` ranking

<div class="quality-summary" markdown="1">

| Rank | Stemmer | Balanced accuracy | Over-stemming (OI) | Under-stemming (UI) |
|---:|---|---:|---:|---:|
|1|Radixor|0.950991|0.000000%|9.801848%|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|0.868094|0.000838%|26.380368%|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|0.867636|0.000852%|26.472040%|

</div>

<details class="quality-details" markdown="1"><summary>Classification metrics</summary>

| Rank | Stemmer | Output policy | Precision | Recall | Specificity | Balanced accuracy | Pairwise accuracy | Error rate |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|PRIMARY_OUTPUT|1.000000|0.901982|1.000000|0.950991|0.999981|0.000019|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|PRIMARY_OUTPUT|0.945609|0.736196|0.999992|0.868094|0.999939|0.000061|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|PRIMARY_OUTPUT|0.944646|0.735280|0.999991|0.867636|0.999939|0.000061|

</details>

<details class="quality-details" markdown="1"><summary>Pair-relation metrics</summary>

| Rank | Stemmer | Output policy | F0.5 | F1 | F2 | Jaccard | Fowlkes–Mallows | MCC |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|PRIMARY_OUTPUT|0.978728|0.948465|0.920017|0.901982|0.949727|0.949718|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|PRIMARY_OUTPUT|0.894709|0.827865|0.770315|0.706288|0.834359|0.834331|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|PRIMARY_OUTPUT|0.893748|0.826916|0.769384|0.704908|0.833414|0.833386|

</details>

<details class="quality-details" markdown="1"><summary>Raw pair counts</summary>

| Rank | Stemmer | Output policy | TP | FP | FN | TN | Over error / possible | Under error / possible |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|PRIMARY_OUTPUT|25582|0|2780|143394154|0 / 143394154|2780 / 28362|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|PRIMARY_OUTPUT|20880|1201|7482|143392953|1201 / 143394154|7482 / 28362|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|PRIMARY_OUTPUT|20854|1222|7508|143392932|1222 / 143394154|7508 / 28362|

</details>

#### `ANY_CANDIDATE` oracle bounds

These results are measured, not missing. `ANY_CANDIDATE` answers two separate optimistic questions for each pair: a gold-related pair avoids under-stemming when the candidate sets intersect, while a gold-negative pair avoids over-stemming when some non-colliding candidate selection exists. The oracle may choose a different candidate for the same word in different pairs. Consequently, these decisions do not form one globally realizable predicted relation or one TP/FP/FN/TN confusion matrix. Balanced accuracy, F-scores, Jaccard, Fowlkes–Mallows, and MCC are therefore mathematically **not applicable**, rather than unknown.

<div class="quality-summary quality-summary--oracle" markdown="1">

| Stemmer | Optimistic over-stemming (OI) | Optimistic under-stemming (UI) |
|---|---:|---:|
|Radixor|0.000000%|0.000000%|

</div>

<details class="quality-details" markdown="1"><summary>Oracle-bound pair counts</summary>

| Stemmer | Unavoidable over errors / gold-negative pairs | Unrepairable under errors / gold-related pairs |
|---|---:|---:|
|Radixor|0 / 143394154|0 / 28362|

</details>

#### `ALL_CANDIDATES` ranking

<div class="quality-summary" markdown="1">

| Rank | Stemmer | Balanced accuracy | Over-stemming (OI) | Under-stemming (UI) |
|---:|---|---:|---:|---:|
|1|Radixor|1.000000|0.000000%|0.000000%|

</div>

<details class="quality-details" markdown="1"><summary>Classification metrics</summary>

| Rank | Stemmer | Output policy | Precision | Recall | Specificity | Balanced accuracy | Pairwise accuracy | Error rate |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|ALL_CANDIDATES|1.000000|1.000000|1.000000|1.000000|1.000000|0.000000|

</details>

<details class="quality-details" markdown="1"><summary>Pair-relation metrics</summary>

| Rank | Stemmer | Output policy | F0.5 | F1 | F2 | Jaccard | Fowlkes–Mallows | MCC |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|ALL_CANDIDATES|1.000000|1.000000|1.000000|1.000000|1.000000|1.000000|

</details>

<details class="quality-details" markdown="1"><summary>Raw pair counts</summary>

| Rank | Stemmer | Output policy | TP | FP | FN | TN | Over error / possible | Under error / possible |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|ALL_CANDIDATES|28362|0|0|143394154|0 / 143394154|0 / 28362|

</details>

#### Multi-output analysis

Alternative candidates are capability analyses, not replacements for the deterministic comparison.

| Stemmer | Under pairs repaired | Best-case over pairs avoided | All-candidate collisions added | Multi-candidate forms | Multi-candidate share | Maximum candidates | Total candidate assignments |
|---|---:|---:|---:|---:|---:|---:|---:|
|Radixor|2780|0|0|1091|6.441519%|5|18255|

### `LOWERCASE_GROUPS_ONLY`

This mode contains **5 result rows**, **3 evaluated stemmers**, and **3 output policies**. Applied-row and form counts are shown per row because adapters share the language corpus but policy rows remain independently auditable. `PRIMARY_OUTPUT` and `ALL_CANDIDATES` rankings are ordered by unrounded balanced accuracy, followed by MCC, F1, over-stemming rate, over-stemming count, under-stemming rate, and stemmer. `ANY_CANDIDATE` has no single rank metric and is listed alphabetically. Balanced accuracy is a navigation metric, not a universally authoritative quality score.

#### `PRIMARY_OUTPUT` ranking

<div class="quality-summary" markdown="1">

| Rank | Stemmer | Balanced accuracy | Over-stemming (OI) | Under-stemming (UI) |
|---:|---|---:|---:|---:|
|1|Radixor|0.951104|0.000000%|9.779191%|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|0.868252|0.000841%|26.348702%|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|0.867846|0.000841%|26.429959%|

</div>

<details class="quality-details" markdown="1"><summary>Classification metrics</summary>

| Rank | Stemmer | Output policy | Precision | Recall | Specificity | Balanced accuracy | Pairwise accuracy | Error rate |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|PRIMARY_OUTPUT|1.000000|0.902208|1.000000|0.951104|0.999981|0.000019|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|PRIMARY_OUTPUT|0.945528|0.736513|0.999992|0.868252|0.999939|0.000061|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|PRIMARY_OUTPUT|0.945471|0.735700|0.999992|0.867846|0.999939|0.000061|

</details>

<details class="quality-details" markdown="1"><summary>Pair-relation metrics</summary>

| Rank | Stemmer | Output policy | F0.5 | F1 | F2 | Jaccard | Fowlkes–Mallows | MCC |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|PRIMARY_OUTPUT|0.978782|0.948590|0.920206|0.902208|0.949846|0.949837|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|PRIMARY_OUTPUT|0.894744|0.828034|0.770581|0.706534|0.834502|0.834474|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|PRIMARY_OUTPUT|0.894463|0.827499|0.769862|0.705755|0.834016|0.833989|

</details>

<details class="quality-details" markdown="1"><summary>Raw pair counts</summary>

| Rank | Stemmer | Output policy | TP | FP | FN | TN | Over error / possible | Under error / possible |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|PRIMARY_OUTPUT|25537|0|2768|142869660|0 / 142869660|2768 / 28305|
|2|SNOWBALL NORWEGIAN NYNORSK DIRECT|PRIMARY_OUTPUT|20847|1201|7458|142868459|1201 / 142869660|7458 / 28305|
|3|SNOWBALL NORWEGIAN NYNORSK LUCENE FILTER|PRIMARY_OUTPUT|20824|1201|7481|142868459|1201 / 142869660|7481 / 28305|

</details>

#### `ANY_CANDIDATE` oracle bounds

These results are measured, not missing. `ANY_CANDIDATE` answers two separate optimistic questions for each pair: a gold-related pair avoids under-stemming when the candidate sets intersect, while a gold-negative pair avoids over-stemming when some non-colliding candidate selection exists. The oracle may choose a different candidate for the same word in different pairs. Consequently, these decisions do not form one globally realizable predicted relation or one TP/FP/FN/TN confusion matrix. Balanced accuracy, F-scores, Jaccard, Fowlkes–Mallows, and MCC are therefore mathematically **not applicable**, rather than unknown.

<div class="quality-summary quality-summary--oracle" markdown="1">

| Stemmer | Optimistic over-stemming (OI) | Optimistic under-stemming (UI) |
|---|---:|---:|
|Radixor|0.000000%|0.000000%|

</div>

<details class="quality-details" markdown="1"><summary>Oracle-bound pair counts</summary>

| Stemmer | Unavoidable over errors / gold-negative pairs | Unrepairable under errors / gold-related pairs |
|---|---:|---:|
|Radixor|0 / 142869660|0 / 28305|

</details>

#### `ALL_CANDIDATES` ranking

<div class="quality-summary" markdown="1">

| Rank | Stemmer | Balanced accuracy | Over-stemming (OI) | Under-stemming (UI) |
|---:|---|---:|---:|---:|
|1|Radixor|1.000000|0.000000%|0.000000%|

</div>

<details class="quality-details" markdown="1"><summary>Classification metrics</summary>

| Rank | Stemmer | Output policy | Precision | Recall | Specificity | Balanced accuracy | Pairwise accuracy | Error rate |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|ALL_CANDIDATES|1.000000|1.000000|1.000000|1.000000|1.000000|0.000000|

</details>

<details class="quality-details" markdown="1"><summary>Pair-relation metrics</summary>

| Rank | Stemmer | Output policy | F0.5 | F1 | F2 | Jaccard | Fowlkes–Mallows | MCC |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|ALL_CANDIDATES|1.000000|1.000000|1.000000|1.000000|1.000000|1.000000|

</details>

<details class="quality-details" markdown="1"><summary>Raw pair counts</summary>

| Rank | Stemmer | Output policy | TP | FP | FN | TN | Over error / possible | Under error / possible |
|---:|---|---|---:|---:|---:|---:|---:|---:|
|1|Radixor|ALL_CANDIDATES|28305|0|0|142869660|0 / 142869660|0 / 28305|

</details>

#### Multi-output analysis

Alternative candidates are capability analyses, not replacements for the deterministic comparison.

| Stemmer | Under pairs repaired | Best-case over pairs avoided | All-candidate collisions added | Multi-candidate forms | Multi-candidate share | Maximum candidates | Total candidate assignments |
|---|---:|---:|---:|---:|---:|---:|---:|
|Radixor|2768|0|0|1086|6.423755%|5|18219|

### Output Policies and Metric Definitions

Each distinct surface form is one item and may belong to several gold groups. Two forms are gold-related when their membership sets intersect; a relation shared by several groups is counted once. `PRIMARY_OUTPUT` uses one deterministic stem per form. `ANY_CANDIDATE` is an optimistic oracle-assisted pairwise upper bound: a gold-related pair succeeds when candidates intersect, while a gold-negative pair succeeds when a non-colliding selection exists. Candidate choices may differ between pairs, so this is not deterministic runtime behaviour and does not define one confusion matrix. `ALL_CANDIDATES` activates every returned candidate; forms are related when candidate sets intersect.

For `PRIMARY_OUTPUT` and `ALL_CANDIDATES`, `TP = underPossiblePairs - underErrorPairs`, `FN = underErrorPairs`, `FP = overErrorPairs`, and `TN = overPossiblePairs - overErrorPairs`. `ANY_CANDIDATE` publishes only its separate oracle-assisted under/over bounds; confusion-derived metrics are mathematically inapplicable and are not presented in its language-page section. Their machine-readable CSV fields remain empty. Undefined metric denominators in otherwise applicable policies are rendered as `n/a`.

- Under-stemming rate (Paice UI): `FN / (TP + FN)`, the false-negative rate over gold-related pairs.
- Over-stemming rate (Paice OI): `FP / (TN + FP)`, the false-positive rate over gold-negative pairs.
- Pairwise precision: `TP / (TP + FP)`, the fraction of predicted conflations that are gold-standard positive pairs.
- Pairwise recall: `TP / (TP + FN)`, the fraction of gold-standard positive pairs successfully connected.
- Pairwise specificity: `TN / (TN + FP)`, the fraction of gold-negative pairs correctly separated.
- Balanced accuracy: `(recall + specificity) / 2`. It gives equal weight to positive and negative pair classes and is less dominated by the large true-negative class than ordinary accuracy. It does not replace the raw errors or other metrics.
- Pairwise F-beta: `((1 + betaSquared) * TP) / (((1 + betaSquared) * TP) + (betaSquared * FN) + FP)`. F0.5 emphasizes precision and penalizes over-stemming more; F1 weights precision and recall equally; F2 emphasizes recall and penalizes under-stemming more.
- MCC: `(TP * TN - FP * FN) / sqrt((TP + FP) * (TP + FN) * (TN + FP) * (TN + FN))`. It uses all confusion counts and remains useful under class imbalance, except when its denominator is degenerate.
- Jaccard index: `TP / (TP + FP + FN)`.
- Fowlkes–Mallows index: `sqrt(precision * recall)`.
- Pairwise accuracy: `(TP + TN) / (TP + TN + FP + FN)`. It can be dominated by true-negative cross-group pairs.
- Pairwise error rate: `(FP + FN) / (TP + TN + FP + FN)`.

Standard ARI, homogeneity, completeness, V-measure, and NMI are not calculated: their usual contingency-table definitions require an exclusive gold partition, while this gold standard is an overlapping cover.

### Provenance

- Authoritative source: `docs/benchmarks/data/stemming-quality.csv`
- Source SHA-256: `edf16b07be8a535943ddf37caeb8807755c95e9e1fb13244145f28be74b491d8`
- Evaluation command: `./gradlew stemmingQuality --no-daemon`
- Dictionary language: `NN_NO`
- Processing modes: `ALL_WORDS`, `LOWERCASE_GROUPS_ONLY`
- Stemmer versions and transitive artifacts: resolved by the repository's JMH Gradle configuration and `gradle.lockfile`
- Model ID, version, and SHA-256: recorded in every CSV row
- Run date, core source state, JDK, operating system, and hardware: recorded on the [benchmark environment page](../reference/environment.md)

<!-- STEMMING-QUALITY:END -->