|
|
--- |
|
|
language: hyw |
|
|
language_name: Western 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: 4.072 |
|
|
- name: best_isotropy |
|
|
type: isotropy |
|
|
value: 0.8364 |
|
|
- name: vocabulary_size |
|
|
type: vocab |
|
|
value: 0 |
|
|
generated: 2026-01-10 |
|
|
--- |
|
|
|
|
|
# Western Armenian - Wikilangs Models |
|
|
## Comprehensive Research Report & Full Ablation Study |
|
|
|
|
|
This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Western Armenian** Wikipedia data. |
|
|
We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings. |
|
|
|
|
|
## ๐ 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 |
|
|
|
|
|
 |
|
|
|
|
|
### 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 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
### Results |
|
|
|
|
|
| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens | |
|
|
|------------|-------------|---------------|----------|--------------| |
|
|
| **8k** | 3.186x | 3.19 | 0.2260% | 265,032 | |
|
|
| **16k** | 3.511x | 3.52 | 0.2491% | 240,461 | |
|
|
| **32k** | 3.812x | 3.82 | 0.2705% | 221,471 | |
|
|
| **64k** | 4.072x ๐ | 4.08 | 0.2889% | 207,332 | |
|
|
|
|
|
### Tokenization Examples |
|
|
|
|
|
Below are sample sentences tokenized with each vocabulary size: |
|
|
|
|
|
**Sample 1:** `ีฉีธึีกีฏีกีถ, ีธีน ีถีกีฐีกีถีป ีฟีกึีซ, 17ึีค ีคีกึีธึ 89ึีค ีฟีกึีซีถ ีง ิดีงีบึีฅึ ิพีถีธึีถีคีถีฅึ 16px 120px ีีธีถ...` |
|
|
|
|
|
| Vocab | Tokens | Count | |
|
|
|-------|--------|-------| |
|
|
| 8k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+28 more)` | 38 | |
|
|
| 16k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+27 more)` | 37 | |
|
|
| 32k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+26 more)` | 36 | |
|
|
| 64k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+26 more)` | 36 | |
|
|
|
|
|
**Sample 2:** `ีฉีธึีกีฏีกีถ, ีธีน ีถีกีฐีกีถีป ีฟีกึีซ, 17ึีค ีคีกึีธึ 69ึีค ีฟีกึีซีถ ีง ิดีงีบึีฅึ ิฑีถีฎีกีถึ
ีฉ ีกีดีฝีกีฉีซึีธีพี ีีฝีดีกีถ...` |
|
|
|
|
|
| Vocab | Tokens | Count | |
|
|
|-------|--------|-------| |
|
|
| 8k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+30 more)` | 40 | |
|
|
| 16k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+27 more)` | 37 | |
|
|
| 32k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+27 more)` | 37 | |
|
|
| 64k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 7 ึีค ... (+26 more)` | 36 | |
|
|
|
|
|
**Sample 3:** `ีฉีธึีกีฏีกีถ, ีธีน ีถีกีฐีกีถีป ีฟีกึีซ, 16ึีค ีคีกึีธึ 70ึีค ีฟีกึีซีถ ีง ิดีงีบึีฅึ ิพีถีธึีถีคีถีฅึ 16px 120px ีีฅีบ...` |
|
|
|
|
|
| Vocab | Tokens | Count | |
|
|
|-------|--------|-------| |
|
|
| 8k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 6 ึีค ... (+33 more)` | 43 | |
|
|
| 16k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 6 ึีค ... (+33 more)` | 43 | |
|
|
| 32k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 6 ึีค ... (+32 more)` | 42 | |
|
|
| 64k | `โีฉีธึีกีฏีกีถ , โีธีน โีถีกีฐีกีถีป โีฟีกึีซ , โ 1 6 ึีค ... (+30 more)` | 40 | |
|
|
|
|
|
|
|
|
### Key Findings |
|
|
|
|
|
- **Best Compression:** 64k achieves 4.072x compression |
|
|
- **Lowest UNK Rate:** 8k with 0.2260% 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 | 39,006 | 15.25 | 104,315 | 8.5% | 23.6% | |
|
|
| **2-gram** | Subword | 392 ๐ | 8.61 | 9,402 | 59.8% | 96.3% | |
|
|
| **3-gram** | Word | 62,599 | 15.93 | 104,125 | 4.4% | 14.0% | |
|
|
| **3-gram** | Subword | 3,216 | 11.65 | 76,613 | 26.7% | 64.9% | |
|
|
| **4-gram** | Word | 113,012 | 16.79 | 154,212 | 2.7% | 9.7% | |
|
|
| **4-gram** | Subword | 17,012 | 14.05 | 379,918 | 14.1% | 37.8% | |
|
|
| **5-gram** | Word | 73,099 | 16.16 | 96,541 | 3.1% | 11.9% | |
|
|
| **5-gram** | Subword | 58,403 | 15.83 | 935,209 | 8.5% | 24.3% | |
|
|
|
|
|
### Top 5 N-grams by Size |
|
|
|
|
|
**2-grams (Word):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีฅีฒีกีฎ ีง` | 5,851 | |
|
|
| 2 | `ีดีงีป ีฏีจ` | 5,372 | |
|
|
| 3 | `ีฅึ ีฏีจ` | 4,686 | |
|
|
| 4 | `ีธึ ีฏีจ` | 4,419 | |
|
|
| 5 | `ีซีถีนีบีงีฝ ีถีกีฅึ` | 3,890 | |
|
|
|
|
|
**3-grams (Word):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีฎีกีถึ
ีฉีกีฃึีธึีฉีซึีถีถีฅึ ีกึีฟีกึีซีถ ีตีฒีธึีดีถีฅึ` | 1,448 | |
|
|
| 2 | `ีฟีฅีฒีซ ีฏ ีธึีถีฅีถีกีต` | 1,025 | |
|
|
| 3 | `ีฟีฅ ีฝ ีถีกีฅึ` | 875 | |
|
|
| 4 | `ีฌีธีตีฝ ีฟีฅีฝีกีฎ ีง` | 799 | |
|
|
| 5 | `ีฏีฅีถีฝีกีฃึีธึีฉีซึีถ ีฎีถีกีฎ ีง` | 685 | |
|
|
|
|
|
**4-grams (Word):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีฐ ีด ีจ ีด` | 449 | |
|
|
| 2 | `ีฏีฅีถีฝีกีฃึีกีฏีกีถ ีฃีซีฎีฅึ ีฎีถีกีฎ ีง` | 395 | |
|
|
| 3 | `ีฉีธึีกีฏีกีถ ีธีน ีถีกีฐีกีถีป ีฟีกึีซ` | 330 | |
|
|
| 4 | `ีด ีจ ีด ีซ` | 326 | |
|
|
| 5 | `ีถีกีญีถีกีฏีกีถ ีฏึีฉีธึีฉีซึีถีจ ีฝีฟีกึีกีฎ ีง` | 273 | |
|
|
|
|
|
**5-grams (Word):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีฐ ีด ีจ ีด ีซ` | 320 | |
|
|
| 2 | `ีฟีกึีซีถ ีง ีคีงีบึีฅึ ีฎีถีธึีถีคีถีฅึ 16px` | 223 | |
|
|
| 3 | `ีกีฒีขีซึึีถีฅึ ีฐีกีต ีฐีกีถึีกีฃีซีฟีกีฏ ีฐ ีดีฏึีฟีซีน` | 148 | |
|
|
| 4 | `ีง ีคีงีบึีฅึ ีฎีถีธึีถีคีถีฅึ 16px ีดีกีฐีฅึ` | 147 | |
|
|
| 5 | `ีคีงีบึีฅึ ีฎีถีธึีถีคีถีฅึ 16px ีดีกีฐีฅึ 16px` | 147 | |
|
|
|
|
|
**2-grams (Subword):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีธ ึ` | 1,154,928 | |
|
|
| 2 | `ีก ีถ` | 1,111,749 | |
|
|
| 3 | `ีถ _` | 917,764 | |
|
|
| 4 | `ีฅ ึ` | 685,736 | |
|
|
| 5 | `ีก ึ` | 622,298 | |
|
|
|
|
|
**3-grams (Subword):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีก ีถ _` | 382,604 | |
|
|
| 2 | `ีถ ีฅ ึ` | 314,903 | |
|
|
| 3 | `ึ ีธ ึ` | 295,790 | |
|
|
| 4 | `ีก ีฏ ีก` | 277,056 | |
|
|
| 5 | `ีธ ึ ีฉ` | 265,013 | |
|
|
|
|
|
**4-grams (Subword):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีก ีฏ ีก ีถ` | 217,395 | |
|
|
| 2 | `ีฏ ีก ีถ _` | 159,498 | |
|
|
| 3 | `ีฅ ึ ีธ ึ` | 152,660 | |
|
|
| 4 | `ีธ ึ ีฉ ีซ` | 140,761 | |
|
|
| 5 | `ีฉ ีซ ึ ีถ` | 139,607 | |
|
|
|
|
|
**5-grams (Subword):** |
|
|
|
|
|
| Rank | N-gram | Count | |
|
|
|------|--------|-------| |
|
|
| 1 | `ีก ีฏ ีก ีถ _` | 153,426 | |
|
|
| 2 | `ีธ ึ ีฉ ีซ ึ` | 138,505 | |
|
|
| 3 | `ึ ีฉ ีซ ึ ีถ` | 138,493 | |
|
|
| 4 | `ีธ ึ ีฉ ีฅ ีก` | 106,369 | |
|
|
| 5 | `ีถ ีฅ ึ ีธ ึ` | 105,374 | |
|
|
|
|
|
|
|
|
### Key Findings |
|
|
|
|
|
- **Best Perplexity:** 2-gram (subword) with 392 |
|
|
- **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 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
### Results |
|
|
|
|
|
| Context | Variant | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability | |
|
|
|---------|---------|-------------|------------|------------------|-----------------|----------------| |
|
|
| **1** | Word | 0.8813 | 1.842 | 6.94 | 388,915 | 11.9% | |
|
|
| **1** | Subword | 0.5894 | 1.505 | 6.80 | 3,661 | 41.1% | |
|
|
| **2** | Word | 0.2276 | 1.171 | 1.57 | 2,695,260 | 77.2% | |
|
|
| **2** | Subword | 0.9532 | 1.936 | 6.36 | 24,911 | 4.7% | |
|
|
| **3** | Word | 0.0665 | 1.047 | 1.11 | 4,212,072 | 93.4% | |
|
|
| **3** | Subword | 0.8254 | 1.772 | 4.29 | 158,342 | 17.5% | |
|
|
| **4** | Word | 0.0190 ๐ | 1.013 | 1.03 | 4,666,447 | 98.1% | |
|
|
| **4** | Subword | 0.6377 | 1.556 | 2.87 | 679,042 | 36.2% | |
|
|
|
|
|
### Generated Text Samples (Word-based) |
|
|
|
|
|
Below are text samples generated from each word-based Markov chain model: |
|
|
|
|
|
**Context Size 1:** |
|
|
|
|
|
1. `ีฅึ ีณีธีถ ีนีซึ ีซีถึ ีกึีคีงีถ ีกีตีค ึีกีตีฌีจ ีทึีปีกีถีจ ีฟีกีฝีจ ีฃีซึึีฅึีจ ีฃึีธึีกีฎ ีฐีกีตีฅึีงีถ ีกีถีฃีฌีฅึีงีถ ีธึ ีฏ ีกีผีถีง` |
|
|
2. `ีง ีฉีธึีกีฏีกีถีถีฅึีธึีถ ีจีฝีฟ ีชีธีฒีธีพึีคีกีฏีกีถ ีกึีคีซีฝีฟีซ ีฏีธีนีดีกีถ ีฐีกีตีกีฝีฟีกีถีซ ีฐีกีถึีกีบีฅีฟีธึีฉีฅีกีถ ีฏีกีผีกีพีกึีธึีฉีฅีกีถ ีฝีกีฏีกีตีถ ีกีถ ีซึ ีด...` |
|
|
3. `ีฏีจ ีบีกีฟีฝีบีกึีง ึีกีถีกีฟีกีฏีกีถ ีฏีธีฒีดีงีถ ีฅึีฃีจ ีฑีกีตีถีกีฃึีธึีกีฎ ีง ีบีกึีธึีซ 1 ึีค ีฏีกีฉีธีฒีซีฏีธีฝ ีญีธึีงีถ ีฟีงึ ีฏีซึึีฅีฒีฅีกีถ ีฟีกีตีกีถีก 8` |
|
|
|
|
|
**Context Size 2:** |
|
|
|
|
|
1. `ีฅีฒีกีฎ ีง ีฐีกีต ีกึีทีกีฏีธึีถีซีถีฅึีธึ ีกึึีกีตีกีฟีธีฐีดีงีถ ีฅีฒีกีฎ ีง 100 ีฐีกีฆีกึีงีถ ีกึีฅีฌีซ ีฐีกีต ีบีกีฟีกีถีซีถีฅึ ีชีกีดีกีถีกีฏีกีฃึีธึีฉีซึีถ 15 ึีฅ...` |
|
|
2. `ีดีงีป ีฏีจ ีฃีฟีถีธึีซีถ ึีซีดึีซีถ ีกีดีขีธีฒีป ีฟีกึีกีฎึีซีถ ีดีฅีฎ ีฏีกีฒีถีซีซ ีกีถีฟีกีผีถีฅึีจ ีกึีฃีฅีฌีธึีซีถ ีฆีกึีคีจ ีฏีจ ีฏีกีฆีดีฅีถ ีซึ ีกีทีญีกีฟีธึีฉีซึีถีถ...` |
|
|
3. `ีฅึ ีฏีจ ีพีฅึีกีคีกีผีถีกีต ีฅึีธึีฝีกีฒีงีด ีฏ ีฅึีฉีกีถ ีฃีฅึีฅีฆีดีกีถ ีกีถีธึีทีกีขีธีตึ ีซึีฒีฅึีธีพ ึ
ีฎีฅีฌีธึ ึึีซีฝีฟีธีฝีซ ีดีกึีดีซีถีจ ีซึ ีดีฟีกีฐีธีฃีธึีฉีซ...` |
|
|
|
|
|
**Context Size 3:** |
|
|
|
|
|
1. `ีฎีกีถึ
ีฉีกีฃึีธึีฉีซึีถีถีฅึ ีกึีฟีกึีซีถ ีตีฒีธึีดีถีฅึ ีกีตีฝึ
ึ ีฅึีปีกีถีฏีธึีฉีตีกีถ ีดีซีปีกีฆีฃีกีตีซีถ ึ
ึีถ ีง ีจีฝีฟ ีพีซีณีกีฏีกีฃึีธึีฉีฅีกีถ ีฃีซึีฒีกึีซ ีฏีก...` |
|
|
2. `ีฟีฅีฒีซ ีฏ ีธึีถีฅีถีกีต ีพีซีฆีซ ีพีซึีกีขีธึีชีกีฏีกีถ ีฃีธึีฎีธีฒีธึีฉีซึีถีถีฅึีธึ ีจีถีฉีกึึีซีถ ีฅึ ีตีกีฟีฏีกีบีงีฝ ึีถีกีถีกีฌีง ีกีผีกีป ีฝีฟีธึีฅึ ีฏีจ ีถีฅึีฏีก...` |
|
|
3. `ีฟีฅ ีฝ ีถีกีฅึ ีกึีฅึีดีฟีกีฐีกีตีกีฝีฟีกีถีซ ีฅึ ีกึีฅึีดีฟีกีฐีกีตีธึีฉีฅีกีถ ีฐีกึึีฅึีธึ ีธึีฝีธึีดีถีกีฝีซึีธึีฉีฅีกีถ ีฏีฅีคึีธีถ ีผีกีฟีซึ
ีฅีกีถ ีกีถีฏีกีญ ีฐีกีต...` |
|
|
|
|
|
**Context Size 4:** |
|
|
|
|
|
1. `ีฐ ีด ีจ ีด ีซ ีกึีชีกีถีฅีกึ ีทึีกีถีทีกีถีธีพ ีญึ
ีฝึีฅึ ีฐ ีด ีจ ีด ีซ ีฏีฅีคึีธีถีกีฏีกีถ ีพีกึีนีธึีฉีซึีถีจ ีฃีถีกีฐีกีฟีฅีฌีธีพ ีขีกีฆีดีกีพีกีฝีฟีกีฏ ีฅีฒีขึ
ึ ีฅึ...` |
|
|
2. `ีฏีฅีถีฝีกีฃึีกีฏีกีถ ีฃีซีฎีฅึ ีฎีถีกีฎ ีง ีฏีซึีธีพีกีฏีกีถีซ ีดีงีป ีกีตีชีด ีพีกีถีกีฑีธึ ีฏีจ ีฌีธึีฝีกีขีกีถีงึ ีทึีปีกีถีซ ีกึีคีซึีถีกีขีฅึีกีฏีกีถ ีฅึ ีฃีซึีฒีกีฟีถีฟ...` |
|
|
3. `ีฉีธึีกีฏีกีถ ีธีน ีถีกีฐีกีถีป ีฟีกึีซ 19ึีค ีคีกึีธึ ีพีฅึีปีซีถ 100ึีค ีฟีกึีซีถ ีง ีคีงีบึีฅึ ีกีถีฝีฟีธีตีฃ ีกีดีฝีกีฉีซึีธีพ ีกึีฉีธึึ ีงีพีกีถีฝ ึีถีธีฝีธีฝีซ...` |
|
|
|
|
|
|
|
|
### Generated Text Samples (Subword-based) |
|
|
|
|
|
Below are text samples generated from each subword-based Markov chain model: |
|
|
|
|
|
**Context Size 1:** |
|
|
|
|
|
1. `_ีดีงีปีธึีฉีฅีดีถ_ีฏีกีฏีีก` |
|
|
2. `ีกีถ_ีกึีฐีกีถ_ีฏีกึีธึีจ_` |
|
|
3. `ีถึึ_ีฃีธึีซีฝีธึึีธึึีช` |
|
|
|
|
|
**Context Size 2:** |
|
|
|
|
|
1. `ีธึีฉีฅีกีถึีถีฅีฌ_ีกีถ)_ีฐีก` |
|
|
2. `ีกีถีถีฅึีจ_ีบีกีฟึีธึีกีฎีกีถ` |
|
|
3. `ีถ_ีบีกึีซีถ_ีดีงีฟ_ีฐีกึีกึ` |
|
|
|
|
|
**Context Size 3:** |
|
|
|
|
|
1. `ีกีถ_ีฟีกึีขีฅึีธีฝ,_17-ึีค` |
|
|
2. `ีถีฅึีจ:_ีกีถ_ีฏีกีฟีกึีกีบีฅีฟ` |
|
|
3. `ึีธึีฉีซึีถีถีฅึีธีพึ_ีฐึ
ึีจ` |
|
|
|
|
|
**Context Size 4:** |
|
|
|
|
|
1. `ีกีฏีกีถีธึีกีฆีกีฏยป_(ยซretur` |
|
|
2. `ีฏีกีถ_ีฏึีฉีกีฏีกีตีถ_ีฐีกีดีกึึ` |
|
|
3. `ีฅึีธึ_ีฃีธึีฝีฟีฅีฒีฎีกีฃีธึีฎีธ` |
|
|
|
|
|
|
|
|
### Key Findings |
|
|
|
|
|
- **Best Predictability:** Context-4 (word) with 98.1% predictability |
|
|
- **Branching Factor:** Decreases with context size (more deterministic) |
|
|
- **Memory Trade-off:** Larger contexts require more storage (679,042 contexts) |
|
|
- **Recommendation:** Context-3 or Context-4 for text generation |
|
|
|
|
|
--- |
|
|
## 4. Vocabulary Analysis |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
### Statistics |
|
|
|
|
|
| Metric | Value | |
|
|
|--------|-------| |
|
|
| Vocabulary Size | 163,300 | |
|
|
| Total Tokens | 4,777,649 | |
|
|
| Mean Frequency | 29.26 | |
|
|
| Median Frequency | 4 | |
|
|
| Frequency Std Dev | 646.35 | |
|
|
|
|
|
### Most Common Words |
|
|
|
|
|
| Rank | Word | Frequency | |
|
|
|------|------|-----------| |
|
|
| 1 | ีฅึ | 137,926 | |
|
|
| 2 | ีง | 124,125 | |
|
|
| 3 | ีฏีจ | 121,199 | |
|
|
| 4 | ีดีงีป | 80,008 | |
|
|
| 5 | ีฏ | 34,717 | |
|
|
| 6 | ีธึ | 32,222 | |
|
|
| 7 | ีฅีถ | 28,873 | |
|
|
| 8 | ีซึ | 27,391 | |
|
|
| 9 | ีดีจ | 25,115 | |
|
|
| 10 | ีธึ | 24,951 | |
|
|
|
|
|
### Least Common Words (from vocabulary) |
|
|
|
|
|
| Rank | Word | Frequency | |
|
|
|------|------|-----------| |
|
|
| 1 | ีฐีกึีกีฟีธึีซ | 2 | |
|
|
| 2 | ricลur | 2 | |
|
|
| 3 | ึีกีดีกึีกีดีฅึีฑ | 2 | |
|
|
| 4 | ีดีธึีถึ | 2 | |
|
|
| 5 | munch | 2 | |
|
|
| 6 | ีฐีกีดีกีชีกีดีฅึีธึีกีฎ | 2 | |
|
|
| 7 | measurable | 2 | |
|
|
| 8 | ีฉีฐ | 2 | |
|
|
| 9 | indelible | 2 | |
|
|
| 10 | ีบึีธีคีซีธึีฝึ | 2 | |
|
|
|
|
|
### Zipf's Law Analysis |
|
|
|
|
|
| Metric | Value | |
|
|
|--------|-------| |
|
|
| Zipf Coefficient | 0.9253 | |
|
|
| Rยฒ (Goodness of Fit) | 0.997096 | |
|
|
| Adherence Quality | **excellent** | |
|
|
|
|
|
### Coverage Analysis |
|
|
|
|
|
| Top N Words | Coverage | |
|
|
|-------------|----------| |
|
|
| Top 100 | 26.8% | |
|
|
| Top 1,000 | 48.9% | |
|
|
| Top 5,000 | 67.7% | |
|
|
| Top 10,000 | 76.1% | |
|
|
|
|
|
### Key Findings |
|
|
|
|
|
- **Zipf Compliance:** Rยฒ=0.9971 indicates excellent adherence to Zipf's law |
|
|
- **High Frequency Dominance:** Top 100 words cover 26.8% of corpus |
|
|
- **Long Tail:** 153,300 words needed for remaining 23.9% coverage |
|
|
|
|
|
--- |
|
|
## 5. Word Embeddings Evaluation |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
### 5.1 Cross-Lingual Alignment |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
### 5.2 Model Comparison |
|
|
|
|
|
| Model | Dimension | Isotropy | Semantic Density | Alignment R@1 | Alignment R@10 | |
|
|
|-------|-----------|----------|------------------|---------------|----------------| |
|
|
| **mono_32d** | 32 | 0.8364 | 0.3396 | N/A | N/A | |
|
|
| **mono_64d** | 64 | 0.7779 | 0.2555 | N/A | N/A | |
|
|
| **mono_128d** | 128 | 0.7701 | 0.1665 | N/A | N/A | |
|
|
| **aligned_32d** | 32 | 0.8364 ๐ | 0.3355 | 0.0500 | 0.2460 | |
|
|
| **aligned_64d** | 64 | 0.7779 | 0.2492 | 0.0600 | 0.2960 | |
|
|
| **aligned_128d** | 128 | 0.7701 | 0.1670 | 0.1080 | 0.4300 | |
|
|
|
|
|
### Key Findings |
|
|
|
|
|
- **Best Isotropy:** aligned_32d with 0.8364 (more uniform distribution) |
|
|
- **Semantic Density:** Average pairwise similarity of 0.2522. Lower values indicate better semantic separation. |
|
|
- **Alignment Quality:** Aligned models achieve up to 10.8% 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 | **-0.511** | 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` | ีกีฝีฅีฒีถีกีฃีธึีฎีงีซีถ, ีกีบีกีฏีกีถีซีน, ีกีถีคีกีดีกีฏึีธึีฉีซึีถีจ | |
|
|
| `-ีด` | ีดีธีถีฏีธีฌีซีกีถ, ีดีฟีฅึีซีดีจ, ีดีกีฆีดีฆีธึีฏีถีฅึีธึ | |
|
|
| `-ีดีก` | ีดีกีฆีดีฆีธึีฏีถีฅึีธึ, ีดีกึีซีถ, ีดีกีฟีถีธึีฉีซึีถ | |
|
|
| `-ีฐีก` | ีฐีกึีกึีธึีกีฎีถีฅึีจ, ีฐีกึีถีกีฎ, ีฐีกีฏีกีฆีฃีกีตีซีถ | |
|
|
| `-ีฝ` | ีฝีฉีฅีดึีธึีฟ, ีฝีกึีธีฝ, ีฝีกึีธึีญีกีถีฅีกีถีจ | |
|
|
| `-ีฏ` | ีฏีกีตีกีฆีธึีซ, ีฏีกีตึีงีปีซ, ีฏีกีฟีธึีถ | |
|
|
| `-ีฐ` | ีฐีกึีกึีธึีกีฎีถีฅึีจ, ีฐีกึีถีกีฎ, ีฐีกีฏีกีฆีฃีกีตีซีถ | |
|
|
| `-ีบ` | ีบีธีฃีธีคีซีถีซ, ีบีฅีทีกีพีกึ, ีบีกีฟีฝีบีกึีธึีซ | |
|
|
|
|
|
#### Productive Suffixes |
|
|
| Suffix | Examples | |
|
|
|--------|----------| |
|
|
| `-ีถ` | ีขีกีผีกึีกีถีกีฃีซีฟีกีฏีกีถ, ีขีกีฏีฅึีถ, ีฐีกีฏีกีฆีฃีกีตีซีถ | |
|
|
| `-ีกีถ` | ีขีกีผีกึีกีถีกีฃีซีฟีกีฏีกีถ, ึีกีผีธึีคีกีฏีกีถ, ีฟีธึึีซีฝีฟีกีฏีกีถ | |
|
|
| `-ีจ` | ีฃีธึีฌีบีกีถีฅึีจ, ีฆีฃีกีตีกึีกีถึีจ, ีฐีกึีกึีธึีกีฎีถีฅึีจ | |
|
|
| `-ีซ` | ีฏีกีตีกีฆีธึีซ, ีผีกีฟีซึ
ีฐีฅีผีกีฝึีผีธึีดีซ, ีฏีกีตึีงีปีซ | |
|
|
| `-ีซีถ` | ีฐีกีฏีกีฆีฃีกีตีซีถ, ึ
ึึีงีกีฝีซีถ, ีกีฝีฅีฒีถีกีฃีธึีฎีงีซีถ | |
|
|
| `-ีธึ` | ีถีธีตีถีกีฏีกีถีกึีถีฅีฌีธึ, ึึีธึีฅีฝีธึีถีฅึีธึ, ีธึีฝีธึึีกีถีฅีฌีธึ | |
|
|
| `-ึีถ` | ีฏีกีฟีธึีถ, ีฅีฏีกีดีธึีฟีถีฅึีธึีถ, ีฃีถีธีฒีถีฅึีธึีถ | |
|
|
| `-ึ` | ีซีถีฟีฅึีกีฏีฟีซึ, ีถีธีตีถีกีฏีกีถีกึีถีฅีฌีธึ, ึึีธึีฅีฝีธึีถีฅึีธึ | |
|
|
|
|
|
### 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 | |
|
|
|------|----------|------------------|----------| |
|
|
| `ีถีฅึีธ` | 1.91x | 133 contexts | ีถีฅึีธีพ, ีถีฅึีธีฒ, ีถีฅึีธึ | |
|
|
| `ีธึีฉีฅ` | 1.66x | 232 contexts | ีฌีธึีฉีฅึ, ีธึีฉีฅีกีถ, ีฐีธึีฉีฅีถ | |
|
|
| `ีกีฝีฟีก` | 1.66x | 159 contexts | ีฐีกีฝีฟีก, ึีกีฝีฟีก, ีคีกีฝีฟีก | |
|
|
| `ีกีถีถีฅ` | 1.51x | 178 contexts | ีขีกีถีถีฅึ, ีดีฏีกีถีถีฅึ, ีฝีบีกีถีถีฅึ | |
|
|
| `ึีกีฏีก` | 1.48x | 146 contexts | ึีกีฏีกีถ, ึึีกีฏีก, ีบึีกีฏีกีถ | |
|
|
| `ีธึีกีฏ` | 1.95x | 43 contexts | ีกีผีธึีกีฏ, ีฝึีธึีกีฏีซ, ีกีผีธึีกีฏีซ | |
|
|
| `ีกีฏีธึ` | 1.42x | 179 contexts | ีดีกีฏีธึ, ีกีฏีธึีฌ, ีฏีกีฏีธึีฒ | |
|
|
| `ึีฉีฅีก` | 1.97x | 41 contexts | ีธึีฉีฅีกีถ, ีฎีธึีฉีฅีกีถ, ึีธึีฉีฅีกีถ | |
|
|
| `ีกีดีกึ` | 1.47x | 135 contexts | ึีกีดีกึ, ีกีดีกึีจ, ีฐีกีดีกึ | |
|
|
| `ีกีฃึีธ` | 1.55x | 84 contexts | ีฎึีกีฃึีธีพ, ีฆีกีฃึีธีฝีซ, ีขีถีกีฃึีธีพ | |
|
|
| `ึีฉีซึ` | 1.70x | 48 contexts | ีธึีฉีซึีถ, ีธึีฉีซึีถีจ, ีงีธึีฉีซึีถ | |
|
|
| `ีถีถีฅึ` | 1.47x | 88 contexts | ึีซีถีถีฅึ, ีซีธีถีถีฅึ, ีขีกีถีถีฅึ | |
|
|
|
|
|
### 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` | 244 words | ีกึีกีฎีฅึีดีกีถ, ีกีดีธึีฝีถีกีถีกีถ | |
|
|
| `-ีด` | `-ีถ` | 158 words | ีดีฟีฅึีซีดีถีฅึีงีถ, ีดีฅีฎีฅึีซีถ | |
|
|
| `-ีฏ` | `-ีถ` | 109 words | ีฏีซีฝีกึีธีนีธึีธึีกีฏีกีถ, ีฏึีฅีฟีกึีซีซีถ | |
|
|
| `-ีก` | `-ีจ` | 95 words | ีกีผีกีปีถีธึีฉีซึีถีถีฅึีจ, ีกึีกีฏีกีถีจ | |
|
|
| `-ีก` | `-ีซ` | 89 words | ีกึีซีกึีซ, ีกึีกีดีกีถีซ | |
|
|
| `-ีฝ` | `-ีถ` | 88 words | ีฝีฟีฅีฒีถีฅึีธึีถ, ีฝีกีฉีกีดีฅีกีถีซีถ | |
|
|
| `-ีบ` | `-ีถ` | 88 words | ีบีกึีฉีธีถ, ีบีกีฟีดีกีฌีฅีฆีธึีกีฃึีกีฏีกีถ | |
|
|
| `-ีก` | `-ีกีถ` | 85 words | ีกึีกีฎีฅึีดีกีถ, ีกีดีธึีฝีถีกีถีกีถ | |
|
|
| `-ีด` | `-ีซ` | 84 words | ีดีกีฐีฟีฅีฝีฅีกีถีซ, ีดีกีฒึีฅีบีซ | |
|
|
| `-ีฐีก` | `-ีถ` | 80 words | ีฐีกีดีกีฝีฟีฅีฒีธึีฉีซึีถ, ีฐีกึีกึีกีฏีกีถีซีถ | |
|
|
|
|
|
### 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 | |
|
|
|------|-----------------|------------|------| |
|
|
| ีฎีกีถึ
ีฉีกึีถีฅีฌ | **`ีฎีกีถึ
ีฉีกึ-ีถ-ีฅีฌ`** | 7.5 | `ีถ` | |
|
|
| ีฅึีฏึีกีนีกึีธึีฉีซึีถีจ | **`ีฅึีฏึีกีนีกึีธึีฉีซึ-ีถ-ีจ`** | 7.5 | `ีถ` | |
|
|
| ีกีญีฟีกีบีกีฟีณีกีผีถีฅึีถ | **`ีกีญีฟีกีบีกีฟีณีกีผีถ-ีฅึ-ีถ`** | 7.5 | `ีฅึ` | |
|
|
| ีฐีธีพีซีฟีถีฅึีธีพ | **`ีฐีธีพีซีฟีถ-ีฅึ-ีธีพ`** | 7.5 | `ีฅึ` | |
|
|
| ึีงีฐีฅีกีตีฅีกีถีจ | **`ึีงีฐีฅีกีตีฅีก-ีถ-ีจ`** | 7.5 | `ีถ` | |
|
|
| ีณีงีบีงีณีฅีกีถีซ | **`ีณีงีบีงีณีฅ-ีกีถ-ีซ`** | 7.5 | `ีกีถ` | |
|
|
| ีฑีฃีกีถีถีฅึีธึีถ | **`ีฑีฃีกีถีถีฅึ-ีธึ-ีถ`** | 7.5 | `ีธึ` | |
|
|
| ีดีซีกีขีกีถีธึีฉีซึีถีถีฅึ | **`ีดีซีกีขีกีถีธึีฉีซึีถ-ีถ-ีฅึ`** | 7.5 | `ีถ` | |
|
|
| ีฐีกีถึีกีบีฅีฟีธึีฉีฅีถีงีถ | **`ีฐีกีถึีกีบีฅีฟีธึีฉีฅ-ีถ-ีงีถ`** | 7.5 | `ีถ` | |
|
|
| ีซีดีกีฝีฟีกีฝีซึีธึีฉีฅีถีงีถ | **`ีซีดีกีฝีฟีกีฝีซึีธึีฉีฅ-ีถ-ีงีถ`** | 7.5 | `ีถ` | |
|
|
| ีฟีฅีฒีกีถีธึีถีถีฅึีซ | **`ีฟีฅีฒีกีถีธึีถีถ-ีฅึ-ีซ`** | 7.5 | `ีฅึ` | |
|
|
| ีฐีกึีฅึีกีถีถีฅึ | **`ีฐีกึีฅึีกีถ-ีถ-ีฅึ`** | 7.5 | `ีถ` | |
|
|
| ีขีฅึีขีฅึีตีกีถีซ | **`ีขีฅึีขีฅึีต-ีกีถ-ีซ`** | 7.5 | `ีกีถ` | |
|
|
| ีกีปีกีฏีซึีถีฅึ | **`ีกีปีกีฏีซึ-ีถ-ีฅึ`** | 7.5 | `ีถ` | |
|
|
| ีดีฉีธึีฉีซึีถีจ | **`ีดีฉีธึีฉีซึ-ีถ-ีจ`** | 7.5 | `ีถ` | |
|
|
|
|
|
### 6.6 Linguistic Interpretation |
|
|
|
|
|
> **Automated Insight:** |
|
|
The language Western 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 |
|
|
|
|
|
 |
|
|
|
|
|
### Production Recommendations |
|
|
|
|
|
| Component | Recommended | Rationale | |
|
|
|-----------|-------------|-----------| |
|
|
| Tokenizer | **64k BPE** | Best compression (4.07x) | |
|
|
| N-gram | **2-gram** | Lowest perplexity (392) | |
|
|
| Markov | **Context-4** | Highest predictability (98.1%) | |
|
|
| 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 |
|
|
|
|
|
- ๐ Website: [wikilangs.org](https://wikilangs.org) |
|
|
- ๐ค Models: [huggingface.co/wikilangs](https://huggingface.co/wikilangs) |
|
|
- ๐ Data: [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly) |
|
|
- ๐ค Author: [Omar Kamali](https://huggingface.co/omarkamali) |
|
|
- ๐ค Sponsor: [Featherless AI](https://featherless.ai) |
|
|
--- |
|
|
*Generated by Wikilangs Models Pipeline* |
|
|
|
|
|
*Report Date: 2026-01-10 03:56:09* |
|
|
|