firozehrazavi commited on
Commit
e11acae
·
verified ·
1 Parent(s): bdc87d7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -11
README.md CHANGED
@@ -1,14 +1,30 @@
1
- # Word Embedding Benchmarking
 
 
 
 
 
 
 
2
 
3
- This repository benchmarks Word2Vec embeddings under different configurations
4
- and evaluates their impact on semantic similarity, analogy reasoning,
5
- and downstream text classification tasks.
6
 
7
- ## Highlights
8
- - Systematic Word2Vec hyperparameter study
9
- - Intrinsic evaluation using WordSim353 and BATS
10
- - Qualitative semantic analysis
11
- - Downstream text classification comparison
12
 
13
- ## Best Configuration
14
- Skip-gram | 100 dimensions | window size 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - nlp
4
+ - word2vec
5
+ - embeddings
6
+ - benchmark
7
+ - text-classification
8
+ ---
9
 
10
+ # Word2Vec NLP Benchmarking
 
 
11
 
12
+ This repository contains a notebook to benchmark word embeddings and perform text classification tasks.
 
 
 
 
13
 
14
+ ## Notebook
15
+
16
+ - `wordtovec_nlp.ipynb` : Notebook for evaluating Word2Vec embeddings on text classification benchmarks.
17
+
18
+ ## Description
19
+
20
+ This project demonstrates:
21
+ - Training Word2Vec models (CBOW and Skip-gram)
22
+ - Benchmarking different embedding dimensions
23
+ - Evaluating embeddings on text classification tasks
24
+
25
+ ## Usage
26
+
27
+ Clone the repository and open the notebook:
28
+
29
+ ```bash
30
+ git clone https://huggingface.co/<your-username>/<repo-name>