hy / README.md
omarkamali's picture
Upload all models and assets for hy (latest)
06085d0 verified
---
language: hy
language_name: Armenian
language_family: armenian
tags:
- wikilangs
- nlp
- tokenizer
- embeddings
- n-gram
- markov
- wikipedia
- feature-extraction
- sentence-similarity
- tokenization
- n-grams
- markov-chain
- text-mining
- fasttext
- babelvec
- vocabulous
- vocabulary
- monolingual
- family-armenian
license: mit
library_name: wikilangs
pipeline_tag: text-generation
datasets:
- omarkamali/wikipedia-monthly
dataset_info:
name: wikipedia-monthly
description: Monthly snapshots of Wikipedia articles across 300+ languages
metrics:
- name: best_compression_ratio
type: compression
value: 5.067
- name: best_isotropy
type: isotropy
value: 0.7690
- name: vocabulary_size
type: vocab
value: 0
generated: 2026-01-10
---
# Armenian - Wikilangs Models
## Comprehensive Research Report & Full Ablation Study
This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Armenian** Wikipedia data.
We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.
## ๐Ÿ“‹ 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
![Performance Dashboard](visualizations/performance_dashboard.png)
### Analysis and Evaluation
- [1. Tokenizer Evaluation](#1-tokenizer-evaluation)
- [2. N-gram Model Evaluation](#2-n-gram-model-evaluation)
- [3. Markov Chain Evaluation](#3-markov-chain-evaluation)
- [4. Vocabulary Analysis](#4-vocabulary-analysis)
- [5. Word Embeddings Evaluation](#5-word-embeddings-evaluation)
- [6. Morphological Analysis (Experimental)](#6--morphological-analysis-experimental)
- [7. Summary & Recommendations](#7-summary--recommendations)
- [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
- [Visualizations Index](#visualizations-index)
---
## 1. Tokenizer Evaluation
![Tokenizer Compression](visualizations/tokenizer_compression.png)
![Tokenizer Fertility](visualizations/tokenizer_fertility.png)
![Tokenizer OOV](visualizations/tokenizer_oov.png)
![Total Tokens](visualizations/tokenizer_total_tokens.png)
### Results
| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens |
|------------|-------------|---------------|----------|--------------|
| **8k** | 3.834x | 3.86 | 0.1591% | 2,659,955 |
| **16k** | 4.305x | 4.33 | 0.1786% | 2,368,713 |
| **32k** | 4.718x | 4.75 | 0.1958% | 2,161,366 |
| **64k** | 5.067x ๐Ÿ† | 5.10 | 0.2102% | 2,012,394 |
### Tokenization Examples
Below are sample sentences tokenized with each vocabulary size:
**Sample 1:** `ิฑีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ ึีกีถีฏ ิฑีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ ึีกีถีฏ ิฑีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ ึีกีถีฏ | || || 12 ีฐีธีฏีฟีฅีดีขีฅึ€ || ิฟีซ...`
| Vocab | Tokens | Count |
|-------|--------|-------|
| 8k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+12 more)` | 22 |
| 16k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+9 more)` | 19 |
| 32k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+9 more)` | 19 |
| 64k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+9 more)` | 19 |
**Sample 2:** `ิฑีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ ึีกีถีฏ ิฑีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ ึีกีถีฏ ิฑีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ ึีกีถีฏ | || || 13 ีกีบึ€ีซีฌ || ิฟีกีฟีกีฌีซ...`
| Vocab | Tokens | Count |
|-------|--------|-------|
| 8k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+10 more)` | 20 |
| 16k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+10 more)` | 20 |
| 32k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+8 more)` | 18 |
| 64k | `โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–ีกีฝีฟีฅึ€ีธีซีคีถีฅึ€ีซ โ–ึีกีถีฏ โ–| โ–|| โ–|| โ– ... (+8 more)` | 18 |
**Sample 3:** `ิดึ€ีตีกีชีถีธ, ีขีถีกีฏีกีพีกีตึ€ีฅึ€ีซ ีกีถีธึ‚ีถีถีฅึ€ี ิฒีฅีฌีกีผีธึ‚ีฝีซีก ิดึ€ีตีกีชีถีธ - ีฃีตีธึ‚ีฒีกีฏ ีŽีซีฟีฅีขีฝีฏีซ ีทึ€ีปีกีถีธึ‚ีด, ...`
| Vocab | Tokens | Count |
|-------|--------|-------|
| 8k | `โ–ีคึ€ ีต ีกีช ีถีธ , โ–ีขีถีกีฏีกีพีกีตึ€ีฅึ€ีซ โ–ีกีถีธึ‚ีถ ีถีฅึ€ี โ–ีขีฅีฌีกีผีธึ‚ีฝ ีซีก ... (+28 more)` | 38 |
| 16k | `โ–ีคึ€ ีต ีกีช ีถีธ , โ–ีขีถีกีฏีกีพีกีตึ€ีฅึ€ีซ โ–ีกีถีธึ‚ีถ ีถีฅึ€ี โ–ีขีฅีฌีกีผีธึ‚ีฝ ีซีก ... (+28 more)` | 38 |
| 32k | `โ–ีคึ€ ีตีกีช ีถีธ , โ–ีขีถีกีฏีกีพีกีตึ€ีฅึ€ีซ โ–ีกีถีธึ‚ีถ ีถีฅึ€ี โ–ีขีฅีฌีกีผีธึ‚ีฝ ีซีก โ–ีคึ€ ... (+25 more)` | 35 |
| 64k | `โ–ีคึ€ ีตีกีช ีถีธ , โ–ีขีถีกีฏีกีพีกีตึ€ีฅึ€ีซ โ–ีกีถีธึ‚ีถ ีถีฅึ€ี โ–ีขีฅีฌีกีผีธึ‚ีฝ ีซีก โ–ีคึ€ ... (+19 more)` | 29 |
### Key Findings
- **Best Compression:** 64k achieves 5.067x compression
- **Lowest UNK Rate:** 8k with 0.1591% 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
![N-gram Perplexity](visualizations/ngram_perplexity.png)
![N-gram Unique](visualizations/ngram_unique.png)
![N-gram Coverage](visualizations/ngram_coverage.png)
### Results
| N-gram | Variant | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
|--------|---------|------------|---------|----------------|------------------|-------------------|
| **2-gram** | Word | 274,089 | 18.06 | 2,048,640 | 5.7% | 17.3% |
| **2-gram** | Subword | 435 ๐Ÿ† | 8.77 | 31,099 | 58.6% | 95.3% |
| **3-gram** | Word | 587,646 | 19.16 | 3,025,054 | 4.6% | 14.3% |
| **3-gram** | Subword | 3,630 | 11.83 | 285,926 | 26.0% | 63.1% |
| **4-gram** | Word | 869,845 | 19.73 | 4,440,732 | 5.7% | 15.5% |
| **4-gram** | Subword | 20,147 | 14.30 | 1,705,625 | 14.0% | 36.8% |
| **5-gram** | Word | 457,726 | 18.80 | 2,884,886 | 8.6% | 20.6% |
| **5-gram** | Subword | 78,248 | 16.26 | 5,627,732 | 8.9% | 23.9% |
### Top 5 N-grams by Size
**2-grams (Word):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€` | 162,524 |
| 2 | `ีง ีธึ€` | 122,895 |
| 3 | `ีฎีกีถีธีฉีกีฃึ€ีธึ‚ีฉีตีธึ‚ีถีถีฅึ€ ีกึ€ีฟีกึ„ีซีถ` | 120,383 |
| 4 | `ีฅีฒีฅีฌ ีง` | 83,997 |
| 5 | `ีง ีฉีพีกีฏีกีถีซ` | 83,509 |
**3-grams (Word):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีฎีกีถีธีฉีกีฃึ€ีธึ‚ีฉีตีธึ‚ีถีถีฅึ€ ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€` | 119,820 |
| 2 | `ีทึ€ีปีกีถีซ ีขีถีกีฏีกีพีกีตึ€ีฅึ€ ีฃีตีธึ‚ีฒีฅึ€` | 35,523 |
| 3 | `ีด ีฉ ีก` | 25,916 |
| 4 | `ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ีผีธึ‚ีฝีกีฝีฟีกีถีซ` | 19,895 |
| 5 | `ีง ีก ีด` | 19,670 |
**4-grams (Word):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com ีฏีกีตึ„ีธึ‚ีด` | 18,028 |
| 2 | `ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com` | 18,028 |
| 3 | `ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone` | 18,028 |
| 4 | `ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ` | 18,006 |
| 5 | `ีฐีฒีธึ‚ีดีถีฅึ€ ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ` | 18,006 |
**5-grams (Word):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com ีฏีกีตึ„ีธึ‚ีด` | 18,028 |
| 2 | `ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com` | 18,028 |
| 3 | `ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ` | 18,006 |
| 4 | `ีฐีฒีธึ‚ีดีถีฅึ€ ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone` | 18,006 |
| 5 | `ีฉีพีกีฏีกีถีซ ีธึ‚ีฏึ€ีกีซีถีกีตีซ ีฐีกีดีกีบีฅีฟีกีฏีกีถ ีดีกึ€ีคีกีฐีกีดีกึ€ีซ ีกึ€ีคีตีธึ‚ีถึ„ีถีฅึ€ีจ` | 17,821 |
**2-grams (Subword):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีธ ึ‚` | 25,191,475 |
| 2 | `ีก ีถ` | 21,219,860 |
| 3 | `ีถ _` | 15,448,243 |
| 4 | `ีฅ ึ€` | 14,542,618 |
| 5 | `ีซ _` | 12,944,110 |
**3-grams (Subword):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีธ ึ‚ ีด` | 7,197,254 |
| 2 | `ีถ ีฅ ึ€` | 6,928,522 |
| 3 | `ีก ีถ _` | 6,546,164 |
| 4 | `ีก ีฏ ีก` | 6,299,916 |
| 5 | `ีฏ ีก ีถ` | 5,484,002 |
**4-grams (Subword):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีก ีฏ ีก ีถ` | 4,881,415 |
| 2 | `ีธ ึ‚ ีฉ ีต` | 4,780,700 |
| 3 | `ีธ ึ‚ ีด _` | 4,302,874 |
| 4 | `ีต ีธ ึ‚ ีถ` | 3,153,212 |
| 5 | `ีฏ ีก ีถ _` | 2,879,683 |
**5-grams (Subword):**
| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ีฉ ีต ีธ ึ‚ ีถ` | 2,857,609 |
| 2 | `ีธ ึ‚ ีฉ ีต ีธ` | 2,854,879 |
| 3 | `ึ‚ ีฉ ีต ีธ ึ‚` | 2,854,454 |
| 4 | `ีก ีฏ ีก ีถ _` | 2,763,929 |
| 5 | `ีธ ึ‚ ีฉ ีต ีก` | 1,924,954 |
### Key Findings
- **Best Perplexity:** 2-gram (subword) with 435
- **Entropy Trend:** Decreases with larger n-grams (more predictable)
- **Coverage:** Top-1000 patterns cover ~24% of corpus
- **Recommendation:** 4-gram or 5-gram for best predictive performance
---
## 3. Markov Chain Evaluation
![Markov Entropy](visualizations/markov_entropy.png)
![Markov Contexts](visualizations/markov_contexts.png)
![Markov Branching](visualizations/markov_branching.png)
### Results
| Context | Variant | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
|---------|---------|-------------|------------|------------------|-----------------|----------------|
| **1** | Word | 0.8583 | 1.813 | 11.08 | 3,072,156 | 14.2% |
| **1** | Subword | 1.3537 | 2.556 | 10.63 | 11,441 | 0.0% |
| **2** | Word | 0.3131 | 1.242 | 2.02 | 34,021,781 | 68.7% |
| **2** | Subword | 0.7180 | 1.645 | 5.38 | 121,571 | 28.2% |
| **3** | Word | 0.1098 | 1.079 | 1.24 | 68,796,040 | 89.0% |
| **3** | Subword | 0.7758 | 1.712 | 4.65 | 653,913 | 22.4% |
| **4** | Word | 0.0398 ๐Ÿ† | 1.028 | 1.07 | 84,964,993 | 96.0% |
| **4** | Subword | 0.6964 | 1.620 | 3.55 | 3,038,021 | 30.4% |
### Generated Text Samples (Word-based)
Below are text samples generated from each word-based Markov chain model:
**Context Size 1:**
1. `ีง ีฐีซีฝีฟีฅึ€ีซีฏีก ีฝีกึ€ึ„ีธึ‚ีด ึ‡ ีซ ีกีผีกีปีซีถ ีบีกึ€ีขีฅึ€ีธึ‚ีฉีตีธึ‚ีถีจ 10 ีจ ีนีฅีถ ีกีถีพีกีถีฅีฌ ีฅีถ ีกีดีฅีถีกีฏีฅึ€ีถีฅึ€ ีงีซีถ ีธึ€ีบีฅีฝ ีขีธึ‚ีฝีกีขีกีถีกีฏีกีถ`
2. `ึ‡ ีถีซีฏีธีฌีกีต ีฝีดีธึ€ีนีฏีธีพ ีกีพีกีฃ ีคีธึ‚ีฝีฟึ€ ีพีกึ€ีฏีกีฎ ีจีฝีฟ ีผีค ีกีผีกีปีซีถ ีฐีกีฏีกึ…ีคีกีตีซีถ ีบีกีทีฟีบีกีถีธึ‚ีฉีตีกีถ ีฟีกีฏ ีง ึ†ีซีฌีดีธึ‚ีด ีฉีพีกีฏีกีถีซีถ ...`
3. `ีฅีถ ีทีกึ€ีซีกีฉีซ ึ…ึ€ีฅีถึ„ีถีฅึ€ีซีถ ีกีผีกีปีกึ€ีฏีธึ‚ีฉีตีธึ‚ีถีถีฅึ€ ีกีถีฅีฌ ีซึ€ ีฐีกึ€ีกีฆีกีฟ ีผีธีฝีฟีฝีฅีฌีดีกีท ีกีฏีธึ‚ีดีข ึ„ีกีถีซ ีธึ€ ึ‡ ีถีก ีฝีฟีฅีฒีฎีฅึ red w...`
**Context Size 2:**
1. `ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ayuntamiento de torrejรณn de velasco la cocina espaรฑola antigua la cocina gitana las...`
2. `ีง ีธึ€ ีกีตีค ีฉีฅีดีกีฟีซีฏีกีตีธีพ ีดีฅีฎ ีฐีกีตีฟีถีซีธึ‚ีฉีตีธึ‚ีถ ีฑีฅีผึ„ ีขีฅึ€ีฅึ ีฌีตีธึ‚ีฏ ีขีฅีฝีธีถีซ ีฌีตีธึ‚ีฝีซ ึ†ีซีฌีดีธึ‚ีด ีดีซีกีชีกีดีกีถีกีฏ ึีธึ‚ึีกีคึ€ีพีธึ‚ีด...`
3. `ีฎีกีถีธีฉีกีฃึ€ีธึ‚ีฉีตีธึ‚ีถีถีฅึ€ ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ะปะธั†ะฐ ัะฐะผะฐั€ัะบะพะน ะณัƒะฑะตั€ะฝะธะธ ะฝะฐ ะณะพะด ัะฟะฑ ั‚ะธะฟะพะณั€ะฐั„ะธั ะผ ะพ ะณ ั†ะธะบะป ะผะธะฝะธะฐั‚ัŽ...`
**Context Size 3:**
1. `ีฎีกีถีธีฉีกีฃึ€ีธึ‚ีฉีตีธึ‚ีถีถีฅึ€ ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ีฏีซีถีธีทีซีฟีก ีกีฝีฟีฅึ€ีธีซีคีจ ึƒีธึ„ึ€ ีดีธีฌีธึ€ีกีฏีถีฅึ€ีซ ีฏีฅีถีฟึ€ีธีถีซ ีฏีกีตึ„ีธึ‚ีด ีธึ‚ีฒีฅีฎึ€ีซ ีฟีพีต...`
2. `ีด ีฉ ีก ii i ีฐีกีฆีกึ€ีกีดีตีกีฏีถีฅึ€ ีถีกีพีธีฌีธีฏ ีฃีตีธึ‚ีฒีซ ีทึ€ีปีกีฏีกีตึ„ีซ ีกีพีกีฆีกีขีฌีธึ‚ึ€ีถีฅึ€ีซึ ีฐีกีพีกึ„ีพีกีฎ ีถีตีธึ‚ีฉีฅึ€ีซ ีทีกึ€ึ„ีธึ‚ีด ีฅีฒีฅีฌ ีฅีถ ...`
3. `ีกึ€ีฟีกึ„ีซีถ ีฐีฒีธึ‚ีดีถีฅึ€ ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com ีฏีกีตึ„ีธึ‚ีด ีขีกีทีฏีธึ€ีฟีธีฝีฟีกีถ ีฐีกีถึ€ีกีบีฅีฟีธึ‚ีฉีตีกีถ ีฆ...`
**Context Size 4:**
1. `ีผีธึ‚ีฝีกีฝีฟีกีถีซ ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com ีฏีกีตึ„ีธึ‚ีด ีฝีดีธีฌีฅีถีฝีฏีซ ีดีกึ€ีฆีซ ีฝีดีธีฌีฅีถีฝีฏีซ ีทึ€ีปีกีถีซ ีฏีกีฆีดีธึ‚ีด ีขีถีกีฏีน...`
2. `ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com ีฏีกีตึ„ีธึ‚ีด ีฌีฅีถีซีถีฃึ€ีกีคีซ ีดีกึ€ีฆีซ ีพีฝึ‡ีธีฌีธีชีฝีฏีซ ีทึ€ีปีกีถีซ ีฏีกีฆีดีธึ‚ีด ีขีถีกีฏีนีธึ‚ีฉีตีธึ‚ีถีจ ีฉีพีกีฏีกีถีซีถ...`
3. `ีชีกีดีกีตีซีถ ีฃีธีฟีซีถีฅึ€ีจ worldtimezone com ีฏีกีตึ„ีธึ‚ีด ีขีกีทีฏีธึ€ีฟีธีฝีฟีกีถ ีฐีกีถึ€ีกีบีฅีฟีธึ‚ีฉีตีกีถ ีธึ‚ึ†ีซีดีฝีฏีซ ีทึ€ีปีกีถีซ ีฏีกีฆีดีธึ‚ีด ีขีถีกีฏีน...`
### Generated Text Samples (Subword-based)
Below are text samples generated from each subword-based Markov chain model:
**Context Size 1:**
1. `_ีง_moronesestour`
2. `ีกีฎีฅึ€ีถีคีฅีถีธึ‚ีถีธีพีกีพีธ`
3. `ีถึ„ีกีตีฅึ€ีฏีฝีฏีธีฌีธีถีนีฅีฝ`
**Context Size 2:**
1. `ีธึ‚ีฉีตีธึ‚ีด_ีดีฅึ€ีซึ„_ีฅีถีค`
2. `ีกีถ_ีฐีฝีฏีพีฅึ€_ีฃีธึ‚ีด,_ีธ`
3. `ีถ_ีณีกึ€ึ‡ีธึ‚ีฉีตีธึ‚ีถึ„_ีฏีก`
**Context Size 3:**
1. `ีธึ‚ีด_ีดีฅีฎ_ีดีฅีฌีธีพ_ีกึ€ีฐีซ`
2. `ีถีฅึ€_ีฏีกีด_ีคีฅ_ีดีฅีถีฟึ€ีธึ‚`
3. `ีกีถ_ีฟีพีตีกีฌีถีฅึ€ีกีฆีดีซีถีนีบ`
**Context Size 4:**
1. `ีกีฏีกีถ_ีคีธีฌีซีพีธึ‚ีฉีตีธึ‚ีถีถีฅ`
2. `ีธึ‚ีฉีตีกีถีจ_ีนีกึƒีซ_ีผีฅีฏีฟีธีถ`
3. `ีธึ‚ีด_ีถึ€ีกีถึ_ีฟีฒีกีดีกึ€ีคีฏีก`
### Key Findings
- **Best Predictability:** Context-4 (word) with 96.0% predictability
- **Branching Factor:** Decreases with context size (more deterministic)
- **Memory Trade-off:** Larger contexts require more storage (3,038,021 contexts)
- **Recommendation:** Context-3 or Context-4 for text generation
---
## 4. Vocabulary Analysis
![Zipf's Law](visualizations/zipf_law.png)
![Top Words](visualizations/top20_words.png)
![Coverage Curve](visualizations/vocab_coverage.png)
### Statistics
| Metric | Value |
|--------|-------|
| Vocabulary Size | 1,233,415 |
| Total Tokens | 101,630,095 |
| Mean Frequency | 82.40 |
| Median Frequency | 4 |
| Frequency Std Dev | 4969.84 |
### Most Common Words
| Rank | Word | Frequency |
|------|------|-----------|
| 1 | ีง | 4,241,724 |
| 2 | ึ‡ | 2,378,989 |
| 3 | ีฅีถ | 1,229,938 |
| 4 | ีงึ€ | 646,182 |
| 5 | ีฉีพีกีฏีกีถีซีถ | 577,819 |
| 6 | ีฉีพีกีฏีกีถีซ | 566,535 |
| 7 | ีธึ€ | 463,952 |
| 8 | ีฐีกีดีกึ€ | 422,395 |
| 9 | ีซ | 378,745 |
| 10 | ีซึ€ | 371,982 |
### Least Common Words (from vocabulary)
| Rank | Word | Frequency |
|------|------|-----------|
| 1 | ีฝีกีถีฃีฏีธึ‚ีถีธึ‚ึ€ | 2 |
| 2 | ีกึ€ีนีฅีฐีธึ‚ีด | 2 |
| 3 | ีผีฅีฃีฅีถีฝีซีธึ‚ีด | 2 |
| 4 | ีคีฅีดีธีฃีธึ€ีฃีกีถีซีถ | 2 |
| 5 | ีทีถีกีบีถ | 2 |
| 6 | ีผีกีฐีดีกีถีธึ‚ีฌีฌีก | 2 |
| 7 | ีฌีกีฏีกีถีพีกีฌ | 2 |
| 8 | ีฌีกีฏีกีถีพีกีฌีถ | 2 |
| 9 | ีกีฏีฌีฅีฐีซ | 2 |
| 10 | jsrn | 2 |
### Zipf's Law Analysis
| Metric | Value |
|--------|-------|
| Zipf Coefficient | 0.9590 |
| Rยฒ (Goodness of Fit) | 0.995010 |
| Adherence Quality | **excellent** |
### Coverage Analysis
| Top N Words | Coverage |
|-------------|----------|
| Top 100 | 25.0% |
| Top 1,000 | 47.2% |
| Top 5,000 | 65.8% |
| Top 10,000 | 73.5% |
### Key Findings
- **Zipf Compliance:** Rยฒ=0.9950 indicates excellent adherence to Zipf's law
- **High Frequency Dominance:** Top 100 words cover 25.0% of corpus
- **Long Tail:** 1,223,415 words needed for remaining 26.5% coverage
---
## 5. Word Embeddings Evaluation
![Embedding Isotropy](visualizations/embedding_isotropy.png)
![Similarity Matrix](visualizations/embedding_similarity.png)
![t-SNE Words](visualizations/tsne_words.png)
![t-SNE Sentences](visualizations/tsne_sentences.png)
### 5.1 Cross-Lingual Alignment
![Alignment Quality](visualizations/embedding_alignment_quality.png)
![Multilingual t-SNE](visualizations/embedding_tsne_multilingual.png)
### 5.2 Model Comparison
| Model | Dimension | Isotropy | Semantic Density | Alignment R@1 | Alignment R@10 |
|-------|-----------|----------|------------------|---------------|----------------|
| **mono_32d** | 32 | 0.7690 | 0.3405 | N/A | N/A |
| **mono_64d** | 64 | 0.7404 | 0.3145 | N/A | N/A |
| **mono_128d** | 128 | 0.6370 | 0.2680 | N/A | N/A |
| **aligned_32d** | 32 | 0.7690 ๐Ÿ† | 0.3747 | 0.1620 | 0.5260 |
| **aligned_64d** | 64 | 0.7404 | 0.3024 | 0.2940 | 0.7100 |
| **aligned_128d** | 128 | 0.6370 | 0.2604 | 0.4280 | 0.8220 |
### Key Findings
- **Best Isotropy:** aligned_32d with 0.7690 (more uniform distribution)
- **Semantic Density:** Average pairwise similarity of 0.3101. Lower values indicate better semantic separation.
- **Alignment Quality:** Aligned models achieve up to 42.8% R@1 in cross-lingual retrieval.
- **Recommendation:** 128d aligned for best cross-lingual performance
---
## 6. Morphological Analysis (Experimental)
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 | **5.000** | High morphological productivity | Reliable analysis |
| Idiomaticity Gap | **-0.140** | 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 |
|--------|----------|
| `-ีก` | ีกีขีกีปีซึ‡, ีกีดีถีฅีฆีซีก, ีกีตีฎีตีกีดีถีฅึ€ |
| `-ีดีก` | ีดีกีคีฏีกีถึ, ีดีกีถีฃีกีฒีถีฅึ€, ีดีกึ€ีคีกีฐีกีทีพีซีถ |
| `-ีฏีก` | ีฏีกีดีบีฅีกีคีธึ€, ีฏีกีพีณีกีบีกีฟ, ีฏีกีขีกึ€ีคีซีถีฏีก |
| `-ีฏ` | ีฏีธีถีธึ€ีกีตีซ, ีฏีกีดีบีฅีกีคีธึ€, ีฏีฅีบีซีฟีกีฌ |
| `-ีฏีธ` | ีฏีธีถีธึ€ีกีตีซ, ีฏีธีถีฟึ€ีกีบีธึ‚ีถีฏีฟีฅึ€ีซ, ีฏีธีดีบีกีถีตีธีถีซ |
| `-ีฐีก` | ีฐีกีดึ…ีฃีฟีกีฃีธึ€ีฎีธึ‚ีดีจ, ีฐีกีตีงีถีฅึ€ีฃีธีซ, ีฐีกึ€ีฏีกีพีธ |
| `-ีฝ` | ีฝีฅีญีดีฅึ, ีฝีฅีฏีฏีธ, ีฝีกีฒีกีฉีฅีฌีตีกีถีถ |
| `-ีด` | ีดีกีคีฏีกีถึ, ีดีกีถีฃีกีฒีถีฅึ€, ีดีฅึ€ีฏีกึีธึ‚ึีซีน |
#### Productive Suffixes
| Suffix | Examples |
|--------|----------|
| `-ีถ` | ีพีฅึ€ีกีขีถีกีฏีซีนีถีฅึ€ีซีถ, ีญีธึ‚ึ€ีกีตีซีถ, ีทึ€ีปีกีถีกีฃีซีฎีถ |
| `-ีซ` | ีฏีธีถีธึ€ีกีตีซ, ีฏีธีถีฟึ€ีกีบีธึ‚ีถีฏีฟีฅึ€ีซ, ีพีซีพีซีซ |
| `-ีจ` | ีฆีกีถีฃีกีฏีกีฟีถีฅึ€ีจ, ีทีฅึ€ีฆีซีถีฃีฅึ€ีจ, ีฌีฅีตีทีดีกีถีซีธีฆีถีฅึ€ีจ |
| `-ีซีถ` | ีพีฅึ€ีกีขีถีกีฏีซีนีถีฅึ€ีซีถ, ีญีธึ‚ึ€ีกีตีซีถ, ีขีฅีถีฆีซีถีซีถ |
| `-ีกีถ` | ีนีฅีขีธีฟีกึ€ึ‡ีฝีฏีกีตีกีถ, ีฏีกึ€ีซีขีซีกีถ, ีถีฅีถีฃีกึƒีธีญีธึ‚ีฉีตีกีถ |
| `-ึ€ีซ` | ีฏีธีถีฟึ€ีกีบีธึ‚ีถีฏีฟีฅึ€ีซ, ีคีกีฟีกีพีธึ€ีถีฅึ€ีซ, ีกีถีฆีฃีกีตีกึีธึ‚ึีซีนีถีฅึ€ีซ |
| `-ึ‚ีด` | ีผีกีฆีดีกีขีฅีดีธึ‚ีด, ีฐีฅีพึ€ีธีถีธึ‚ีด, ีบีกึ€ีขีฅึ€ีกีฃึ€ีธึ‚ีด |
| `-ีด` | ีผีกีฆีดีกีขีฅีดีธึ‚ีด, ีฐีฅีพึ€ีธีถีธึ‚ีด, ีฝีซีฟีฏีธีด |
### 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 |
|------|----------|------------------|----------|
| `ีธึ‚ีฉีต` | 1.85x | 608 contexts | ีธึ‚ีฉีตีกีฏ, ีธึ‚ีฉีตีกีถ, ีธึ‚ีฉีตีธีก |
| `ีถีถีฅึ€` | 1.61x | 522 contexts | ีกีถีถีฅึ€, ีฆีถีถีฅึ€, ีธีถีถีฅึ€ |
| `ึ€ีถีฅึ€` | 1.51x | 463 contexts | ีกึ€ีถีฅึ€, ีฉึ€ีถีฅึ€, ีฌีฅึ€ีถีฅึ€ |
| `ีดีขีฅึ€` | 1.58x | 352 contexts | ีซีดีขีฅึ€, ีฉีดีขีฅึ€, ีญีดีขีฅึ€ |
| `ีกีฟีธึ‚` | 1.40x | 704 contexts | ีขีกีฟีธึ‚, ีฏีกีฟีธึ‚, ีฐีกีฟีธึ‚ |
| `ึ€ีพีกีฎ` | 1.64x | 255 contexts | ีปึ€ีพีกีฎ, ีฐึ€ีพีกีฎ, ีฝึ€ีพีกีฎ |
| `ีฏีถีฅึ€` | 1.49x | 432 contexts | ีดีฏีถีฅึ€, ีฏีถีฅึ€ีฅ, ีฝีฏีถีฅึ€ |
| `ีกีฆีดีก` | 1.60x | 200 contexts | ีฏีกีฆีดีก, ีกีฆีดีกีฉ, ีกีฆีดีกีถ |
| `ึ‚ีดีถีฅ` | 1.69x | 134 contexts | ีธึ‚ีดีถีฅึ€ีซ, ีฐีฒึ‚ีดีถีฅึ€, ีฝีธึ‚ีดีถีฅึ€ |
| `ึ‚ีฉีตีธ` | 1.72x | 115 contexts | ีธึ‚ีฉีตีธีก, ีธึ‚ีฉีตีธึ‚ีถ, ีฌีผีธึ‚ีฉีตีธ |
| `ีทีญีกีฟ` | 1.82x | 71 contexts | ีกีทีญีกีฟ, ีกีทีญีกีฟีฅ, ีกีทีญีกีฟีซ |
| `ีกีฒีกึ„` | 1.73x | 82 contexts | ีดีกีฒีกึ„, ีกีฒีกึ„ีซ, ึ„ีกีฒีกึ„ |
### 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 |
|--------|--------|-----------|----------|
| `-ีก` | `-ีถ` | 126 words | ีกีถีฟีซึ†ีธีถ, ีกีบีกีฏีฅีฃีธึ€ีฎีธึ‚ีฉีตีกีถ |
| `-ีก` | `-ีซ` | 101 words | ีกีฃีถีซีกีตีซ, ีกีพีฟีธีคึ€ีธีดีซ |
| `-ีฝ` | `-ีซ` | 84 words | ีฝีกีซีคีซ, ีฝีกีพีกีชีซ |
| `-ีฝ` | `-ีถ` | 80 words | ีฝีธึีกีบีกีฐีธีพีดีกีถ, ีฝีกีถีคีธีพีซีถ |
| `-ีฏ` | `-ีถ` | 78 words | ีฏีกีดีฅีถึ‡ีซีถ, ีฏีกีฆีดีกีฏีฅึ€ีบีธึ‚ีฉีตีธึ‚ีถีถีฅึ€ีซีถ |
| `-ีฏ` | `-ีซ` | 74 words | ีฏึ€ีซีธีฌีซีฉีธีฝึ†ีฅึ€ีกีตีซ, ีฏีฅีถีฝีกีดีซีปีธึีถีฅึ€ีซ |
| `-ีก` | `-ีจ` | 73 words | ีกึ„ีซีฝีจ, ีกีฃีกึ€ีคีจ |
| `-ีด` | `-ีซ` | 72 words | ีดีกึ„ีฝีซีดีกีฌีซีฆีดีซ, ีดีกีธึ‚ีฝีธีฌีธีฝีซ |
| `-ีด` | `-ีถ` | 68 words | ีดีธึ‚ีฉีซึ‚ีถ, ีดีกีฐีธึ‚ีซีถ |
| `-ีดีก` | `-ีถ` | 55 words | ีดีกีฐีธึ‚ีซีถ, ีดีกีธึ‚ีคีกีถ |
### 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 |
|------|-----------------|------------|------|
| ีฏึ€ีกีฝีถีธีบีธีฌีซีฅ | **`ีฏึ€ีกีฝีถีธีบีธีฌ-ีซ-ีฅ`** | 7.5 | `ีซ` |
| ีคีซีคีฅึ€ีดีถีฅึ€ | **`ีคีซีคีฅึ€ีด-ีถ-ีฅึ€`** | 7.5 | `ีถ` |
| ีฑีถีกีฃีถีคีซีฏีถีฅึ€ | **`ีฑีถีกีฃีถีคีซีฏ-ีถ-ีฅึ€`** | 7.5 | `ีถ` |
| ีพีฅึ€ีกีฐีฝีฏีพีกีฎ | **`ีพีฅึ€ีกีฐีฝีฏ-ีพ-ีกีฎ`** | 7.5 | `ีพ` |
| ีดีฅีฟีกีฏีธีฃีถีซีฟีซีพ | **`ีดีฅีฟีกีฏีธีฃีถีซีฟ-ีซ-ีพ`** | 7.5 | `ีซ` |
| ีพีฅึ€ีกีฐีกีถีฑีถีพีฅีฌ | **`ีพีฅึ€ีกีฐีกีถีฑีถ-ีพ-ีฅีฌ`** | 7.5 | `ีพ` |
| ีซึ€ีกีฏีกีถีธึ‚ีฉีซึ‚ีถ | **`ีซึ€ีกีฏีกีถีธึ‚ีฉ-ีซ-ึ‚ีถ`** | 7.5 | `ีซ` |
| ีฏีธึ‚ีฌีซีขีกีฌีซีซ | **`ีฏีธึ‚ีฌีซีขีกีฌ-ีซ-ีซ`** | 7.5 | `ีซ` |
| ีฐีกีดีกีฝีกึ€ีกีถีซ | **`ีฐีกีดีกีฝีกึ€-ีกีถ-ีซ`** | 7.5 | `ีกีถ` |
| ีถีกีญีกีดีกึ€ีคีซีฏ | **`ีถีกีญีกีดีกึ€ีค-ีซ-ีฏ`** | 7.5 | `ีซ` |
| ีดีกีตึ€ีกีกีฝีบีกีถีจ | **`ีดีกีตึ€ีกีกีฝีบ-ีกีถ-ีจ`** | 7.5 | `ีกีถ` |
| ีดีฟีกีตีถีธึ‚ีฉีตีธึ‚ีถีซึ | **`ีดีฟีกีตีถีธึ‚ีฉีตีธึ‚-ีถ-ีซึ`** | 7.5 | `ีถ` |
| ีดีซีฏึ€ีธีขีซีธีฟีซีกีถ | **`ีดีซีฏึ€ีธีขีซีธีฟ-ีซ-ีกีถ`** | 7.5 | `ีซ` |
| ีฝีฏีฆีขีถีกีฏีกีถีซึ | **`ีฝีฏีฆีขีถีกีฏ-ีกีถ-ีซึ`** | 7.5 | `ีกีถ` |
| ีฟึ€ีซีบีฟีกีดีซีถีถีฅึ€ | **`ีฟึ€ีซีบีฟีกีดีซีถ-ีถ-ีฅึ€`** | 7.5 | `ีถ` |
### 6.6 Linguistic Interpretation
> **Automated Insight:**
The language Armenian shows high morphological productivity. The subword models are significantly more efficient than word models, suggesting a rich system of affixation or compounding.
---
## 7. Summary & Recommendations
![Performance Dashboard](visualizations/performance_dashboard.png)
### Production Recommendations
| Component | Recommended | Rationale |
|-----------|-------------|-----------|
| Tokenizer | **64k BPE** | Best compression (5.07x) |
| N-gram | **2-gram** | Lowest perplexity (435) |
| Markov | **Context-4** | Highest predictability (96.0%) |
| 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) ร— 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.
**Rยฒ (Coefficient of Determination)**
> *Definition:* Measures how well the linear fit explains the frequency-rank relationship. Ranges from 0 to 1.
>
> *Intuition:* Rยฒ near 1.0 means the data closely follows Zipf's law; lower values indicate deviation from expected word frequency patterns.
>
> *What to seek:* Rยฒ > 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
1. **Compare within model families:** Metrics are most meaningful when comparing models of the same type (e.g., 8k vs 64k tokenizer).
2. **Consider trade-offs:** Better performance on one metric often comes at the cost of another (e.g., compression vs. OOV rate).
3. **Context matters:** Optimal values depend on downstream tasks. Text generation may prioritize different metrics than classification.
4. **Corpus influence:** All metrics are influenced by corpus characteristics. Wikipedia text differs from social media or literature.
5. **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](https://huggingface.co/datasets/omarkamali/wikipedia-monthly) - a monthly snapshot of Wikipedia articles across 300+ languages.
### Project
A project by **[Wikilangs](https://wikilangs.org)** - Open-source NLP models for every Wikipedia language.
### Maintainer
[Omar Kamali](https://omarkamali.com) - [Omneity Labs](https://omneitylabs.com)
### Citation
If you use these models in your research, please cite:
```bibtex
@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.
### Links
- ๐ŸŒ Website: [wikilangs.org](https://wikilangs.org)
- ๐Ÿค— Models: [huggingface.co/wikilangs](https://huggingface.co/wikilangs)
- ๐Ÿ“Š Data: [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly)
- ๐Ÿ‘ค Author: [Omar Kamali](https://huggingface.co/omarkamali)
- ๐Ÿค Sponsor: [Featherless AI](https://featherless.ai)
---
*Generated by Wikilangs Models Pipeline*
*Report Date: 2026-01-10 18:05:40*