CSB - Wikilangs Models

Comprehensive Research Report & Full Ablation Study

This repository contains NLP models trained and evaluated by Wikilangs, specifically on CSB Wikipedia data. We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.

📋 Repository Contents

Models & Assets

Tokenizers (8k, 16k, 32k, 64k)
N-gram models (2, 3, 4, 5-gram)
Markov chains (context of 1, 2, 3, 4 and 5)
Subword N-gram and Markov chains
Embeddings in various sizes and dimensions (aligned and unaligned)
Language Vocabulary
Language Statistics

1. Tokenizer Evaluation

Results

Vocab Size	Compression	Avg Token Len	UNK Rate	Total Tokens
8k	3.573x	3.58	0.1681%	180,853
16k	3.908x	3.91	0.1839%	165,322
32k	4.227x	4.23	0.1989%	152,876
64k	4.519x 🏆	4.53	0.2126%	142,981

Tokenization Examples

Below are sample sentences tokenized with each vocabulary size:

Sample 1: Nowô Zelandzkô - je państwã na òstrowach Spòkójnégò Òceanu. w Aùstralëji i Ocean...

Vocab	Tokens	Count
8k	`▁nowô ▁zel an dzkô ▁- ▁je ▁państwã ▁na ▁òst rowa ... (+14 more)`	24
16k	`▁nowô ▁zelan dzkô ▁- ▁je ▁państwã ▁na ▁òstrowach ▁spòkójnégò ▁òceanu ... (+6 more)`	16
32k	`▁nowô ▁zelan dzkô ▁- ▁je ▁państwã ▁na ▁òstrowach ▁spòkójnégò ▁òceanu ... (+5 more)`	15
64k	`▁nowô ▁zelandzkô ▁- ▁je ▁państwã ▁na ▁òstrowach ▁spòkójnégò ▁òceanu . ... (+4 more)`	14

Sample 2: 802 / DCCCII 800 « 801 « 802 » 803 » 804 Wëdarzenia Ùrodzëlë sã Ùmarlë

Vocab	Tokens	Count
8k	`▁ 8 0 2 ▁/ ▁dccc ii ▁ 8 0 ... (+25 more)`	35
16k	`▁ 8 0 2 ▁/ ▁dccc ii ▁ 8 0 ... (+25 more)`	35
32k	`▁ 8 0 2 ▁/ ▁dccc ii ▁ 8 0 ... (+25 more)`	35
64k	`▁ 8 0 2 ▁/ ▁dccc ii ▁ 8 0 ... (+25 more)`	35

Sample 3: Smierdzący bòcónk (Geranium robertianum L.) – to je jednorocznô abò dwalatnô ros...

Vocab	Tokens	Count
8k	`▁smier dzą cy ▁bòc ónk ▁( ge ra nium ▁robert ... (+26 more)`	36
16k	`▁smier dzący ▁bòc ónk ▁( gera nium ▁robert ian um ... (+24 more)`	34
32k	`▁smier dzący ▁bòc ónk ▁( gera nium ▁robert ian um ... (+23 more)`	33
64k	`▁smier dzący ▁bòcónk ▁( geranium ▁robert ian um ▁l .) ... (+21 more)`	31

Key Findings

Best Compression: 64k achieves 4.519x compression
Lowest UNK Rate: 8k with 0.1681% unknown tokens
Trade-off: Larger vocabularies improve compression but increase model size
Recommendation: 32k vocabulary provides optimal balance for production use

2. N-gram Model Evaluation

Results

N-gram	Variant	Perplexity	Entropy	Unique N-grams	Top-100 Coverage	Top-1000 Coverage
2-gram	Word	1,973	10.95	6,252	31.3%	68.4%
2-gram	Subword	459 🏆	8.84	2,759	53.4%	98.1%
3-gram	Word	2,109	11.04	7,761	31.4%	68.9%
3-gram	Subword	3,977	11.96	22,668	18.9%	58.0%
4-gram	Word	3,756	11.88	15,387	27.9%	59.4%
4-gram	Subword	19,041	14.22	103,678	9.9%	32.9%

Top 5 N-grams by Size

2-grams (Word):

Rank	N-gram	Count
1	`to je`	2,509
2	`bùtnowé lënczi`	1,441
3	`ùrodzëlë sã`	991
4	`w gminie`	982
5	`m jin`	873

3-grams (Word):

Rank	N-gram	Count
1	`wëdarzenia ùrodzëlë sã`	849
2	`ùrodzëlë sã ùmarlë`	814
3	`w pòmòrsczim wòjewództwie`	642
4	`p p p`	601
5	`pòmòrsczim wòjewództwie w`	543

4-grams (Word):

Rank	N-gram	Count
1	`wëdarzenia ùrodzëlë sã ùmarlë`	753
2	`p p p p`	566
3	`w pòmòrsczim wòjewództwie w`	537
4	`królestwa i jinëch słowiańsczich`	489
5	`i jinëch słowiańsczich krajów`	489

2-grams (Subword):

Rank	N-gram	Count
1	`c z`	39,994
2	`a _`	39,475
3	`_ w`	38,361
4	`. _`	33,310
5	`_ p`	33,120

3-grams (Subword):

Rank	N-gram	Count
1	`c z i`	17,651
2	`_ w _`	16,987
3	`s c z`	14,602
4	`_ p ò`	12,455
5	`n a _`	11,117

4-grams (Subword):

Rank	N-gram	Count
1	`s c z i`	9,987
2	`c z i _`	8,529
3	`_ j e _`	7,782
4	`é g ò _`	7,756
5	`_ n a _`	6,415

Key Findings

Best Perplexity: 2-gram (subword) with 459
Entropy Trend: Decreases with larger n-grams (more predictable)
Coverage: Top-1000 patterns cover ~33% of corpus
Recommendation: 4-gram or 5-gram for best predictive performance

3. Markov Chain Evaluation

Results

Context	Variant	Avg Entropy	Perplexity	Branching Factor	Unique Contexts	Predictability
1	Word	0.5452	1.459	2.98	81,304	45.5%
1	Subword	1.0127	2.018	7.32	978	0.0%
2	Word	0.1324	1.096	1.26	240,607	86.8%
2	Subword	0.9831	1.977	6.04	7,148	1.7%
3	Word	0.0409	1.029	1.07	299,264	95.9%
3	Subword	0.8865	1.849	4.14	43,078	11.4%
4	Word	0.0201 🏆	1.014	1.03	315,962	98.0%
4	Subword	0.6527	1.572	2.59	178,117	34.7%

Generated Text Samples (Word-based)

Below are text samples generated from each word-based Markov chain model:

Context Size 1:

w gminie wickò w nocë dlô biédnëch robòta jakno dzél wsë czelińskô hëta to béł pòlsczi
je rëba z rodzëznë lycosidae òna rosce m jin na zôczątkù leno w pò ùpôdkù kòmùnizmù
i białków zgòrzałégò zgòrzôłczi pòl jeziora potęgowskie to tak samò rok znoszą od średniowiecza do c...

Context Size 2:

to je dzél gardu grëdządza nad wisłą we zdrojach nova berlyn berlyn nigenberlin berlin berlinichen b...
bùtnowé lënczi tadzino w geògraficznym słowôrzu pòlsczégò królestwa i jinëch słowiańsczich krajów pù...
ùrodzëlë sã ùmarlë stolaté

Context Size 3:

wëdarzenia ùrodzëlë sã ùmarlë lesser giełdziński kòlekcjonéra dokôzów kùńsztu lesser giełdziński gaz...
ùrodzëlë sã ùmarlë kalãdôrz na hewòtny rok juliańsczi 914 915 916 917 918 919 920 921 922 923
w pòmòrsczim wòjewództwie w kartësczim krézu w gminie pòtãgòwò w stołpsczim krézu w gminie przedkòwò...

Context Size 4:

wëdarzenia ùrodzëlë sã ùmarlë kalãdôrz na hewòtny rok juliańsczi 948 949 950 951 952 953 954 955 956...
p p p p p p p p p p p p p p p p p p p
w pòmòrsczim wòjewództwie w kartësczim krézu w òbéńdze gminë somònino tu w szkòle dzece ùczą sã kasz...

Generated Text Samples (Subword-based)

Below are text samples generated from each subword-based Markov chain model:

Context Size 1:

_kaństrdk_gô_òdz
arstk:_todł_dnch
icze_zegòriczëni

Context Size 2:

cziwónégò._maińst
a_spòl.)_terticho
_w_rowimòriart_ka

Context Size 3:

czi,_„roxy_dobis_z
_w_chtërnym_są_z_d
sczé_czajny),_mie_

Context Size 4:

sczi_egipsczégò_pòc
czi_rôtësz_bëc_kòle
_je_człowiańsczi_kò

Key Findings

Best Predictability: Context-4 (word) with 98.0% predictability
Branching Factor: Decreases with context size (more deterministic)
Memory Trade-off: Larger contexts require more storage (178,117 contexts)
Recommendation: Context-3 or Context-4 for text generation

4. Vocabulary Analysis

Statistics

Metric	Value
Vocabulary Size	28,754
Total Tokens	367,683
Mean Frequency	12.79
Median Frequency	3
Frequency Std Dev	148.11

Most Common Words

Rank	Word	Frequency
1	w	17,439
2	je	7,833
3	i	6,889
4	na	6,729
5	z	5,037
6	to	4,739
7	sã	3,695
8	do	3,401
9	rok	3,185
10	a	2,487

Least Common Words (from vocabulary)

Rank	Word	Frequency
1	szahada	2
2	allaha	2
3	الله	2
4	llāh	2
5	tatarzy	2
6	chtërzy	2
7	prevost	2
8	gwiôzdozbiór	2
9	discover	2
10	krakowska	2

Zipf's Law Analysis

Metric	Value
Zipf Coefficient	0.9905
R² (Goodness of Fit)	0.995948
Adherence Quality	excellent

Coverage Analysis

Top N Words	Coverage
Top 100	36.0%
Top 1,000	63.2%
Top 5,000	79.8%
Top 10,000	87.4%

Key Findings

Zipf Compliance: R²=0.9959 indicates excellent adherence to Zipf's law
High Frequency Dominance: Top 100 words cover 36.0% of corpus
Long Tail: 18,754 words needed for remaining 12.6% coverage

5. Word Embeddings Evaluation

5.1 Cross-Lingual Alignment

Note: Multilingual alignment visualization not available for this language.

5.2 Model Comparison

Model	Dimension	Isotropy	Semantic Density	Alignment R@1	Alignment R@10
mono_32d	32	0.7759 🏆	0.3628	N/A	N/A
mono_64d	64	0.4956	0.3193	N/A	N/A
mono_128d	128	0.1441	0.3257	N/A	N/A

Key Findings

Best Isotropy: mono_32d with 0.7759 (more uniform distribution)
Semantic Density: Average pairwise similarity of 0.3359. Lower values indicate better semantic separation.
Alignment Quality: No aligned models evaluated in this run.
Recommendation: 128d aligned for best cross-lingual performance

6. Morphological Analysis (Experimental)

⚠️ Warning: This language shows low morphological productivity. The statistical signals used for this analysis may be noisy or less reliable than for morphologically rich languages.

This section presents an automated morphological analysis derived from the statistical divergence between word-level and subword-level models. By analyzing where subword predictability spikes and where word-level coverage fails, we can infer linguistic structures without supervised data.

6.1 Productivity & Complexity

Metric	Value	Interpretation	Recommendation
Productivity Index	0.000	Low morphological productivity	⚠️ Likely unreliable
Idiomaticity Gap	-1.000	Low formulaic content	-

6.2 Affix Inventory (Productive Units)

These are the most productive prefixes and suffixes identified by sampling the vocabulary for global substitutability patterns. A unit is considered an affix if stripping it leaves a valid stem that appears in other contexts.

Productive Prefixes

Prefix	Examples
`-pr`	prozã, przerôbianié, prostonórta
`-pò`	pòmòcë, pòtémù, pòmòcnégò

Productive Suffixes

Suffix	Examples
`-a`	plëszka, svôta, jóna
`-ch`	chtërnich, artisticznëch, tarnowsczich
`-ów`	kònkùrsów, splecënków, piesniów
`-zi`	marokańsczi, hélsczi, esteticzi
`-czi`	marokańsczi, hélsczi, esteticzi

6.3 Bound Stems (Lexical Roots)

Bound stems are high-frequency subword units that are semantically cohesive but rarely appear as standalone words. These often correspond to the 'core' of a word that requires inflection or derivation to be valid.

Stem	Cohesion	Substitutability	Examples
`tërn`	2.01x	29 contexts	chtërną, chtërna, chtërnã
`htër`	2.05x	23 contexts	chtërô, chtërë, chtëre
`chtë`	1.91x	27 contexts	chtërô, chtërë, chtëre
`szëb`	1.99x	22 contexts	kaszëb, kaszëbi, kaszëba
`zeni`	1.64x	32 contexts	zenice, ùczenié, ùczeniô
`odzë`	1.79x	22 contexts	rodzëc, rodzënë, godzëną
`stol`	1.78x	20 contexts	stole, stolp, stolpe
`rodz`	1.40x	44 contexts	rodzy, rodze, rodzą
`aszë`	1.91x	14 contexts	kaszëb, kaszëbi, kaszëba
`sczé`	1.41x	30 contexts	rusczé, wąsczé, nisczé
`zëzn`	1.40x	29 contexts	rodzëzna, rodzëznë, żëdzëzna
`zëbs`	2.04x	9 contexts	kaszëbskô, kaszëbskù, kaszëbskò

6.4 Affix Compatibility (Co-occurrence)

This table shows which prefixes and suffixes most frequently co-occur on the same stems, revealing the 'stacking' rules of the language's morphology.

Prefix	Suffix	Frequency	Examples
`-pr`	`-a`	36 words	prałata, prawidła
`-pò`	`-a`	22 words	pòéta, pòetka
`-pr`	`-ów`	19 words	procëmników, przezeblôkańców
`-pò`	`-ch`	15 words	pòlsczich, pòswiãconëch
`-pò`	`-zi`	12 words	pòrénszi, pòwieczi
`-pò`	`-ów`	12 words	pòétów, pòkôzków
`-pr`	`-ch`	10 words	przédnich, prësach
`-pò`	`-czi`	10 words	pòwieczi, pòprôwczi
`-pr`	`-zi`	4 words	prëczkòwsczi, prekmùrsczi
`-pr`	`-czi`	4 words	prëczkòwsczi, prekmùrsczi

6.5 Recursive Morpheme Segmentation

Using Recursive Hierarchical Substitutability, we decompose complex words into their constituent morphemes. This approach handles nested affixes (e.g., prefix-prefix-root-suffix).

Word	Suggested Split	Confidence	Stem
francesczi	`frances-czi`	4.5	`frances`
przebendowsczich	`pr-zebendows-czi-ch`	4.5	`zebendows`
rozmajitéch	`rozmajité-ch`	4.5	`rozmajité`
misyjnych	`misyjny-ch`	4.5	`misyjny`
kòloniach	`kòlonia-ch`	4.5	`kòlonia`
instrumentów	`instrument-ów`	4.5	`instrument`
òpòwiesców	`òpòwiesc-ów`	4.5	`òpòwiesc`
rockòwich	`rockòwi-ch`	4.5	`rockòwi`
nôrodnych	`nôrodny-ch`	4.5	`nôrodny`
kòntinentów	`kòntinent-ów`	4.5	`kòntinent`
chtërnich	`chtërni-ch`	4.5	`chtërni`
pierszëch	`pierszë-ch`	4.5	`pierszë`
napùlsczich	`napùls-czi-ch`	3.0	`napùls`
pòwijôczowatëch	`pò-wijôczowatë-ch`	3.0	`wijôczowatë`
profesorów	`pr-ofesor-ów`	3.0	`ofesor`

6.6 Linguistic Interpretation

Automated Insight: The language CSB appears to be more isolating or has a highly fixed vocabulary. Word-level models perform nearly as well as subword models, indicating fewer productive morphological processes.

7. Summary & Recommendations

Production Recommendations

Component	Recommended	Rationale
Tokenizer	64k BPE	Best compression (4.52x)
N-gram	2-gram	Lowest perplexity (459)
Markov	Context-4	Highest predictability (98.0%)
Embeddings	100d	Balanced semantic capture and isotropy

Appendix: Metrics Glossary & Interpretation Guide

This section provides definitions, intuitions, and guidance for interpreting the metrics used throughout this report.

Tokenizer Metrics

Compression Ratio

Definition: The ratio of characters to tokens (chars/token). Measures how efficiently the tokenizer represents text.

Intuition: Higher compression means fewer tokens needed to represent the same text, reducing sequence lengths for downstream models. A 3x compression means ~3 characters per token on average.

What to seek: Higher is generally better for efficiency, but extremely high compression may indicate overly aggressive merging that loses morphological information.

Average Token Length (Fertility)

Definition: Mean number of characters per token produced by the tokenizer.

Intuition: Reflects the granularity of tokenization. Longer tokens capture more context but may struggle with rare words; shorter tokens are more flexible but increase sequence length.

What to seek: Balance between 2-5 characters for most languages. Arabic/morphologically-rich languages may benefit from slightly longer tokens.

Unknown Token Rate (OOV Rate)

Definition: Percentage of tokens that map to the unknown/UNK token, indicating words the tokenizer cannot represent.

Intuition: Lower OOV means better vocabulary coverage. High OOV indicates the tokenizer encounters many unseen character sequences.

What to seek: Below 1% is excellent; below 5% is acceptable. BPE tokenizers typically achieve very low OOV due to subword fallback.

N-gram Model Metrics

Perplexity

Definition: Measures how "surprised" the model is by test data. Mathematically: 2^(cross-entropy). Lower values indicate better prediction.

Intuition: If perplexity is 100, the model is as uncertain as if choosing uniformly among 100 options at each step. A perplexity of 10 means effectively choosing among 10 equally likely options.

What to seek: Lower is better. Perplexity decreases with larger n-grams (more context). Values vary widely by language and corpus size.

Entropy

Definition: Average information content (in bits) needed to encode the next token given the context. Related to perplexity: perplexity = 2^entropy.

Intuition: High entropy means high uncertainty/randomness; low entropy means predictable patterns. Natural language typically has entropy between 1-4 bits per character.

What to seek: Lower entropy indicates more predictable text patterns. Entropy should decrease as n-gram size increases.

Coverage (Top-K)

Definition: Percentage of corpus occurrences explained by the top K most frequent n-grams.

Intuition: High coverage with few patterns indicates repetitive/formulaic text; low coverage suggests diverse vocabulary usage.

What to seek: Depends on use case. For language modeling, moderate coverage (40-60% with top-1000) is typical for natural text.

Markov Chain Metrics

Average Entropy

Definition: Mean entropy across all contexts, measuring average uncertainty in next-word prediction.

Intuition: Lower entropy means the model is more confident about what comes next. Context-1 has high entropy (many possible next words); Context-4 has low entropy (few likely continuations).

What to seek: Decreasing entropy with larger context sizes. Very low entropy (<0.1) indicates highly deterministic transitions.

Branching Factor

Definition: Average number of unique next tokens observed for each context.

Intuition: High branching = many possible continuations (flexible but uncertain); low branching = few options (predictable but potentially repetitive).

What to seek: Branching factor should decrease with context size. Values near 1.0 indicate nearly deterministic chains.

Predictability

Definition: Derived metric: (1 - normalized_entropy) × 100%. Indicates how deterministic the model's predictions are.

Intuition: 100% predictability means the next word is always certain; 0% means completely random. Real text falls between these extremes.

What to seek: Higher predictability for text generation quality, but too high (>98%) may produce repetitive output.

Vocabulary & Zipf's Law Metrics

Zipf's Coefficient

Definition: The slope of the log-log plot of word frequency vs. rank. Zipf's law predicts this should be approximately -1.

Intuition: A coefficient near -1 indicates the corpus follows natural language patterns where a few words are very common and most words are rare.

What to seek: Values between -0.8 and -1.2 indicate healthy natural language distribution. Deviations may suggest domain-specific or artificial text.

R² (Coefficient of Determination)

Definition: Measures how well the linear fit explains the frequency-rank relationship. Ranges from 0 to 1.

Intuition: R² near 1.0 means the data closely follows Zipf's law; lower values indicate deviation from expected word frequency patterns.

What to seek: R² > 0.95 is excellent; > 0.99 indicates near-perfect Zipf adherence typical of large natural corpora.

Vocabulary Coverage

Definition: Cumulative percentage of corpus tokens accounted for by the top N words.

Intuition: Shows how concentrated word usage is. If top-100 words cover 50% of text, the corpus relies heavily on common words.

What to seek: Top-100 covering 30-50% is typical. Higher coverage indicates more repetitive text; lower suggests richer vocabulary.

Word Embedding Metrics

Isotropy

Definition: Measures how uniformly distributed vectors are in the embedding space. Computed as the ratio of minimum to maximum singular values.

Intuition: High isotropy (near 1.0) means vectors spread evenly in all directions; low isotropy means vectors cluster in certain directions, reducing expressiveness.

What to seek: Higher isotropy generally indicates better-quality embeddings. Values > 0.1 are reasonable; > 0.3 is good. Lower-dimensional embeddings tend to have higher isotropy.

Average Norm

Definition: Mean magnitude (L2 norm) of word vectors in the embedding space.

Intuition: Indicates the typical "length" of vectors. Consistent norms suggest stable training; high variance may indicate some words are undertrained.

What to seek: Relatively consistent norms across models. The absolute value matters less than consistency (low std deviation).

Cosine Similarity

Definition: Measures angular similarity between vectors, ranging from -1 (opposite) to 1 (identical direction).

Intuition: Words with similar meanings should have high cosine similarity. This is the standard metric for semantic relatedness in embeddings.

What to seek: Semantically related words should score > 0.5; unrelated words should be near 0. Synonyms often score > 0.7.

t-SNE Visualization

Definition: t-Distributed Stochastic Neighbor Embedding - a dimensionality reduction technique that preserves local structure for visualization.

Intuition: Clusters in t-SNE plots indicate groups of semantically related words. Spread indicates vocabulary diversity; tight clusters suggest semantic coherence.

What to seek: Meaningful clusters (e.g., numbers together, verbs together). Avoid over-interpreting distances - t-SNE preserves local, not global, structure.

General Interpretation Guidelines

Compare within model families: Metrics are most meaningful when comparing models of the same type (e.g., 8k vs 64k tokenizer).
Consider trade-offs: Better performance on one metric often comes at the cost of another (e.g., compression vs. OOV rate).
Context matters: Optimal values depend on downstream tasks. Text generation may prioritize different metrics than classification.
Corpus influence: All metrics are influenced by corpus characteristics. Wikipedia text differs from social media or literature.
Language-specific patterns: Morphologically rich languages (like Arabic) may show different optimal ranges than analytic languages.

Visualizations Index

Visualization	Description
Tokenizer Compression	Compression ratios by vocabulary size
Tokenizer Fertility	Average token length by vocabulary
Tokenizer OOV	Unknown token rates
Tokenizer Total Tokens	Total tokens by vocabulary
N-gram Perplexity	Perplexity by n-gram size
N-gram Entropy	Entropy by n-gram size
N-gram Coverage	Top pattern coverage
N-gram Unique	Unique n-gram counts
Markov Entropy	Entropy by context size
Markov Branching	Branching factor by context
Markov Contexts	Unique context counts
Zipf's Law	Frequency-rank distribution with fit
Vocab Frequency	Word frequency distribution
Top 20 Words	Most frequent words
Vocab Coverage	Cumulative coverage curve
Embedding Isotropy	Vector space uniformity
Embedding Norms	Vector magnitude distribution
Embedding Similarity	Word similarity heatmap
Nearest Neighbors	Similar words for key terms
t-SNE Words	2D word embedding visualization
t-SNE Sentences	2D sentence embedding visualization
Position Encoding	Encoding method comparison
Model Sizes	Storage requirements
Performance Dashboard	Comprehensive performance overview

About This Project

Data Source

Models trained on wikipedia-monthly - a monthly snapshot of Wikipedia articles across 300+ languages.

Project

A project by Wikilangs - Open-source NLP models for every Wikipedia language.

Maintainer

Omar Kamali - Omneity Labs

Citation

If you use these models in your research, please cite:

@misc{wikilangs2025,
  author = {Kamali, Omar},
  title = {Wikilangs: Open NLP Models for Wikipedia Languages},
  year = {2025},
  doi = {10.5281/zenodo.18073153},
  publisher = {Zenodo},
  url = {https://huggingface.co/wikilangs}
  institution = {Omneity Labs}
}

License

MIT License - Free for academic and commercial use.

CSB - Wikilangs Models

Comprehensive Research Report & Full Ablation Study

📋 Repository Contents

Models & Assets

Analysis and Evaluation

1. Tokenizer Evaluation

Results

Tokenization Examples

Key Findings

2. N-gram Model Evaluation

Results

Top 5 N-grams by Size

Key Findings

3. Markov Chain Evaluation

Results

Generated Text Samples (Word-based)

Generated Text Samples (Subword-based)

Key Findings

4. Vocabulary Analysis

Statistics

Most Common Words

Least Common Words (from vocabulary)

Zipf's Law Analysis

Coverage Analysis

Key Findings

5. Word Embeddings Evaluation

5.1 Cross-Lingual Alignment

5.2 Model Comparison

Key Findings

6. Morphological Analysis (Experimental)

6.1 Productivity & Complexity

6.2 Affix Inventory (Productive Units)

Productive Prefixes

Productive Suffixes

6.3 Bound Stems (Lexical Roots)

6.4 Affix Compatibility (Co-occurrence)

6.5 Recursive Morpheme Segmentation

6.6 Linguistic Interpretation

7. Summary & Recommendations

Production Recommendations

Appendix: Metrics Glossary & Interpretation Guide

Tokenizer Metrics

N-gram Model Metrics

Markov Chain Metrics

Vocabulary & Zipf's Law Metrics

Word Embedding Metrics

General Interpretation Guidelines

Visualizations Index

About This Project

Data Source

Project

Maintainer

Citation

License

Links

Dataset used to train wikilangs/csb