Figure 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Download
View publication
High-level architecture of the ETE framework.

High-level architecture of the ETE framework.

Source publication
Figure 1: Histogram of the number of words per item description in the...
Figure 2: The distribution of items by seller's industry in the invoice...
Figure 3: Histogram of the number of words per item description in the...
Figure 4: The distribution of items by category in the eBay dataset.
+10 Figure 5: High-level architecture of the ETE framework.
Categorizing Items with Short and Noisy Descriptions using Ensembled Transferred Embeddings
Preprint
Full-text available
  • Oct 2021
Item categorization is a machine learning task which aims at classifying e-commerce items, typically represented by textual attributes, to their most suitable category from a predefined set of categories. An accurate item categorization system is essential for improving both the user experience and the operational processes of the company. In this...
Cite
Download full-text

Context in source publication

Context 1
... Ensembled Transferred Embeddings framework is composed of four main steps (see Figure 5): ...

Similar publications

Fig. 1: SS-GAN on top of a pretrained Bangla-BERT model; G produces...
Fig. 2: Accuracy of GAN-Bangla-BERT on BanFakeNews (top) and...
Fig. 3: Confusion matrix of GAN-Bangla-BERT on Bengali-Hate-Speech...
A GAN-BERT Based Approach for Bengali Text Classification with a Few Labeled Examples
Preprint
Full-text available
  • Jul 2022
Basic machine learning algorithms or transfer learning models work well for language categorization, but these models require a vast volume of annotated data. We need a better model to tackle the problem because labeled data is scarce. This problem may have a solution in GAN-BERT. To classify Bengali text, we have developed a GAN-BERT based model,...
View