# azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation architecture

> Architecture diagram of the GitHub repository azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation
- Repository: https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation

## Overview

This repository is a research evaluation suite for comparing Arabic word embeddings on NLP tasks, rather than a hosted application. The workflow is to run a task-specific or combined evaluation script against labeled benchmarks and embedding files, then record accuracy and related metrics. The task scripts cover document categorization, named-entity recognition, part-of-speech tagging, and sentiment analysis; the combined FastText script also includes embedding-oriented evaluations such as analogy and clustering tasks. The excerpts show these as standalone scripts. Because they are partial, some internal details and connections are not represented.

Main entry points: [`Accuracy by NLP tasks_DC.py`](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_DC.py) (Document categorization), [`Accuracy by NLP tasks_NER.py`](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_NER.py) (Named entities), [`Accuracy by NLP tasks_POS.py`](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_POS.py) (Part of speech), [`Accuracy by NLP tasks_SA.py`](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_SA.py) (Sentiment analysis)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_task_eval["Task evaluations"]
  node_dc["Document categorization"]
  node_ner["Named entities"]
  node_pos["Part of speech"]
  node_sa["Sentiment analysis"]
end

subgraph group_combined_eval["Combined evaluation"]
  node_fasttext_suite["Embedding task suite"]
end

node_researcher(("Researcher"))
node_benchmarks["Labeled benchmarks"]
node_embeddings[("Embedding files")]
node_results["Metric files"]

node_researcher -->|"runs"| node_dc
node_researcher -->|"runs"| node_ner
node_researcher -->|"runs"| node_pos
node_researcher -->|"runs"| node_sa
node_researcher -->|"runs"| node_fasttext_suite
node_benchmarks -->|"provides labels"| node_dc
node_benchmarks -->|"provides labels"| node_ner
node_benchmarks -->|"provides labels"| node_pos
node_benchmarks -->|"provides labels"| node_sa
node_benchmarks -->|"provides labels"| node_fasttext_suite
node_embeddings -->|"supplies vectors"| node_dc
node_embeddings -->|"supplies vectors"| node_ner
node_embeddings -->|"supplies vectors"| node_pos
node_embeddings -->|"supplies vectors"| node_sa
node_embeddings -->|"supplies vectors"| node_fasttext_suite
node_dc -->|"writes metrics"| node_results
node_ner -->|"writes metrics"| node_results
node_pos -->|"writes metrics"| node_results
node_sa -->|"writes metrics"| node_results
node_fasttext_suite -->|"writes metrics"| node_results

click node_dc "https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_DC.py"
click node_ner "https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_NER.py"
click node_pos "https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_POS.py"
click node_sa "https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_SA.py"
click node_fasttext_suite "https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/FastText%20All%20accuracies.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_dc,node_ner,node_pos,node_sa toneBlue
class node_fasttext_suite,node_embeddings toneAmber
class node_researcher,node_benchmarks,node_results toneIndigo
```

## Components

### Task evaluations

- [Document categorization](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_DC.py): `Accuracy by NLP tasks_DC.py`
- [Named entities](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_NER.py): `Accuracy by NLP tasks_NER.py`
- [Part of speech](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_POS.py): `Accuracy by NLP tasks_POS.py`
- [Sentiment analysis](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/Accuracy%20by%20NLP%20tasks_SA.py): `Accuracy by NLP tasks_SA.py`

### Combined evaluation

- [Embedding task suite](https://github.com/azchaimae/nlp-applications-with-word-embeddings-models-extrinsic-evaluation/blob/main/FastText%20All%20accuracies.py): `FastText All accuracies.py`

### Other components

- **Researcher**
- **Labeled benchmarks**
- **Embedding files**
- **Metric files**

## Connections

- Researcher → Document categorization: runs (evidence: `README.md`)
- Researcher → Named entities: runs (evidence: `README.md`)
- Researcher → Part of speech: runs (evidence: `README.md`)
- Researcher → Sentiment analysis: runs (evidence: `README.md`)
- Researcher → Embedding task suite: runs (evidence: `README.md`)
- Labeled benchmarks → Document categorization: provides labels (evidence: `Accuracy by NLP tasks_DC.py`)
- Labeled benchmarks → Named entities: provides labels (evidence: `Accuracy by NLP tasks_NER.py`)
- Labeled benchmarks → Part of speech: provides labels (evidence: `Accuracy by NLP tasks_POS.py`)
- Labeled benchmarks → Sentiment analysis: provides labels (evidence: `Accuracy by NLP tasks_SA.py`)
- Labeled benchmarks → Embedding task suite: provides labels (evidence: `FastText All accuracies.py`)
- Embedding files → Document categorization: supplies vectors (evidence: `Accuracy by NLP tasks_DC.py`)
- Embedding files → Named entities: supplies vectors (evidence: `Accuracy by NLP tasks_NER.py`)
- Embedding files → Part of speech: supplies vectors (evidence: `Accuracy by NLP tasks_POS.py`)
- Embedding files → Sentiment analysis: supplies vectors (evidence: `Accuracy by NLP tasks_SA.py`)
- Embedding files → Embedding task suite: supplies vectors (evidence: `FastText All accuracies.py`)
- Document categorization → Metric files: writes metrics (evidence: `Accuracy by NLP tasks_DC.py`)
- Named entities → Metric files: writes metrics (evidence: `Accuracy by NLP tasks_NER.py`)
- Part of speech → Metric files: writes metrics (evidence: `Accuracy by NLP tasks_POS.py`)
- Sentiment analysis → Metric files: writes metrics (evidence: `Accuracy by NLP tasks_SA.py`)
- Embedding task suite → Metric files: writes metrics (evidence: `FastText All accuracies.py`)
