search

Priyanshiguptaaa / Flipkart_Product_Categorization

This repository illustrates the task of applying Machine Translation ( Seq2Seq Attention Network ) for Product Categorization of an E-Commerce Website data (Flipkart), classification of the description of products into the primary category of their category tree, and documenting the path to an optimal model pipeline
4 stars 1 forks source link

Transformer model #3

Open Bouncer51 opened 3 years ago

Bouncer51 commented 3 years ago

Hi,

Have you not completely implemented the Transformer model and seq2seq+ transformer model proposed in "Don’t Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation". Maggie Yundi Li, Liling Tan, Stanley Kok. 2018. https://arxiv.org/pdf/1812.05774.pdf .

Is there any missing parts that is yet to be implemented?

TIA

Priyanshiguptaaa commented 3 years ago

Hi,

Yes, I've implemented it, I'll add it to the repository shortly!

Bouncer51 commented 3 years ago

I Am having some issue in executing training code of seq2seq. I got error like: test variable is not defined anywhere, could you help me find what exactly the variable holds?.

There is a line in code with test['category'].apply(lambda x: category_dictionary[x])

TIA

Update: I have got it working by using test_data instead.

I have achieved accuracy of 92% when trained for 5 Epochs: