|
--- |
|
license: bigscience-openrail-m |
|
pipeline_tag: text-classification |
|
|
|
widget: |
|
- example_title: "Commercial" |
|
text: "custom sports jerseys" |
|
- example_title: "Non-Commercial" |
|
text: "health tips" |
|
- example_title: "Informational" |
|
text: "is cycling healthy" |
|
- example_title: "Navigational" |
|
text: "owayo login page" |
|
- example_title: "Transactional" |
|
text: "buy custom sport jerseys" |
|
- example_title: "Commercial Investigation" |
|
text: "owayo custom jerseys reviews" |
|
- example_title: "Local" |
|
text: "cycling shop in brisbane" |
|
- example_title: "Entertainment" |
|
text: "funny cycling videos" |
|
--- |
|
Multi-label binary sequence classification model developed by [Dejan Marketing](https://dejanmarketing.com/). |
|
|
|
The model is designed to be deployed in an automated pipeline capable of classifying search query intent for thousands (or even millions) of search queries from common data sources such as Google Search Console, SEMRush, Ahrefs, Moz, Majestic and Google Ads. This is a small demo model which may occassionally misclasify some queries. In a typical commercial project a larger model is deployed for the task and in special cases a domain-specific model is developed for the client. |
|
|
|
Interested in using this in an automated pipeline for bulk query processing? [book an appointment](https://dejanmarketing.com/conference/) |
|
|
|
# Base Model |
|
|
|
albert/albert-base-v2 |
|
|
|
# Output |
|
|
|
A list of binary classes (0,1) for 10 classification labels. |
|
|
|
## Labels |
|
|
|
LABEL_0: 'Commercial' |
|
LABEL_1: 'Non-Commercial' |
|
LABEL_2: 'Branded' # Needs-further fine-tuning. |
|
LABEL_3: 'Non-Branded' # Needs-further fine-tuning. |
|
LABEL_4: 'Informational' |
|
LABEL_5: 'Navigational' |
|
LABEL_6: 'Transactional' |
|
LABEL_7: 'Commercial Investigation' |
|
LABEL_8: 'Local' |
|
LABEL_9: 'Entertainment' |
|
|
|
# Sources of Training Data |
|
|
|
## Owayo: |
|
- [USA](https://www.owayo.com/), [Australia](https://www.owayo.com.au/), [Germany](https://www.owayo.de/), [UK](https://www.owayo.co.uk/), [Germany](https://www.owayo.ca/) |
|
|
|
## Others: |
|
- [Leonardo AI](https://leonardo.ai/), [The Wests Group](https://mywests.com.au/), [Zendesk](https://www.zendesk.com/) |
|
|
