Update README.md
Browse files
README.md
CHANGED
|
@@ -15,4 +15,62 @@ tags:
|
|
| 15 |
- electra
|
| 16 |
- bert
|
| 17 |
- review
|
| 18 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
- electra
|
| 16 |
- bert
|
| 17 |
- review
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
### Model Info
|
| 21 |
+
|
| 22 |
+
This model was developed/finetuned for product review task for Turkish Language. Model was finetuned via hepsiburada.com product review dataset.
|
| 23 |
+
|
| 24 |
+
### Model Sources
|
| 25 |
+
|
| 26 |
+
<!-- Provide the basic links for the model. -->
|
| 27 |
+
|
| 28 |
+
- **Dataset:** https://huggingface.co/datasets/anilguven/turkish_product_reviews_sentiment
|
| 29 |
+
- **Paper:** https://ieeexplore.ieee.org/document/9559007
|
| 30 |
+
- **Demo-Coding [optional]:** https://github.com/anil1055/Turkish_Product_Review_Analysis_with_Language_Models
|
| 31 |
+
- **Finetuned from model [optional]:** https://huggingface.co/dbmdz/electra-base-turkish-cased-discriminator
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
## How to Get Started with the Model
|
| 35 |
+
|
| 36 |
+
from transformers import pipeline
|
| 37 |
+
|
| 38 |
+
pipe = pipeline("text-classification", model="anilguven/electra_tr_turkish_product_reviews")
|
| 39 |
+
|
| 40 |
+
or
|
| 41 |
+
|
| 42 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 43 |
+
|
| 44 |
+
tokenizer = AutoTokenizer.from_pretrained("anilguven/electra_tr_turkish_product_reviews")
|
| 45 |
+
|
| 46 |
+
model = AutoModelForSequenceClassification.from_pretrained("anilguven/electra_tr_turkish_product_reviews")
|
| 47 |
+
|
| 48 |
+
#### Preprocessing
|
| 49 |
+
|
| 50 |
+
You must apply removing stopwords, stemming, or lemmatization process for Turkish.
|
| 51 |
+
|
| 52 |
+
### Results
|
| 53 |
+
|
| 54 |
+
Accuracy: %92.54
|
| 55 |
+
|
| 56 |
+
## Citation
|
| 57 |
+
|
| 58 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 59 |
+
|
| 60 |
+
**BibTeX:**
|
| 61 |
+
|
| 62 |
+
@INPROCEEDINGS{9559007,
|
| 63 |
+
author={Guven, Zekeriya Anil},
|
| 64 |
+
booktitle={2021 6th International Conference on Computer Science and Engineering (UBMK)},
|
| 65 |
+
title={The Effect of BERT, ELECTRA and ALBERT Language Models on Sentiment Analysis for Turkish Product Reviews},
|
| 66 |
+
year={2021},
|
| 67 |
+
volume={},
|
| 68 |
+
number={},
|
| 69 |
+
pages={629-632},
|
| 70 |
+
keywords={Computer science;Sentiment analysis;Analytical models;Computational modeling;Bit error rate;Time factors;Random forests;Sentiment Analysis;Language Model;Product Review;Machine Learning;E-commerce},
|
| 71 |
+
doi={10.1109/UBMK52708.2021.9559007}}
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
**APA:**
|
| 75 |
+
|
| 76 |
+
Guven, Z. A. (2021, September). The effect of bert, electra and albert language models on sentiment analysis for turkish product reviews. In 2021 6th International Conference on Computer Science and Engineering (UBMK) (pp. 629-632). IEEE.
|