|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- t5 |
|
|
- department-routing |
|
|
- urgency-detection |
|
|
- intent-detection |
|
|
- multi-label |
|
|
- customer-support |
|
|
- business |
|
|
- complaints |
|
|
license: mit |
|
|
datasets: |
|
|
- Ataur77/ecommerce-customer-support |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
base_model: |
|
|
- google-t5/t5-small |
|
|
new_version: Ataur77/ecommerce-customer-support |
|
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
|
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
This model is designed to classify and respond to customer queries in an eCommerce domain. It processes and categorizes customer queries based on their intent, associated product department, and urgency level, which helps in building an intelligent, automated eCommerce assistant. |
|
|
|
|
|
- **Intent**: The purpose or type of request in the customer’s query (e.g., `Product Inquiry`, `Order Status`, `Return Request`). |
|
|
- **Product Category**: The product category that the query is related to (e.g., `Electronics`, `Clothing`, `Home Appliances`). |
|
|
- **Urgency Level**: The priority of the query (e.g., `Immediate`, `Soon`, `Medium`). |
|
|
|
|
|
The model is based on a **T5 architecture** fine-tuned on a dataset of eCommerce customer queries. This model is useful for building chatbots, virtual assistants, or automated systems that provide customers with efficient responses regarding products, orders, and other services. |
|
|
|
|
|
- **Developed by:** [Ataur Rahman Likon] |
|
|
- **Funded by [optional]:** [More Information Needed] |
|
|
- **Shared by [optional]:** [More Information Needed] |
|
|
- **Model type:** Text Classification |
|
|
- **Language(s) (NLP):** English |
|
|
- **License:** [More Information Needed] |
|
|
- **Finetuned from model [optional]:** T5 |
|
|
|
|
|
### Model Sources [optional] |
|
|
|
|
|
- **Repository:** [Link to the model repository] |
|
|
- **Paper [optional]:** [Link to the associated paper] |
|
|
- **Demo [optional]:** [Link to demo] |
|
|
|
|
|
## Uses |
|
|
|
|
|
### Direct Use |
|
|
|
|
|
This model can be directly used in customer service applications in the eCommerce industry to categorize queries, route them to the appropriate departments, and automate responses to customer queries such as `Order Status`, `Product Availability`, or `Return Process`. |
|
|
|
|
|
### Downstream Use [optional] |
|
|
|
|
|
The model can be integrated into larger systems such as eCommerce platforms, chatbots, customer support software, or virtual assistants. It can also be further fine-tuned for specific eCommerce businesses to classify more specialized queries. |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
The model is not designed for use in non-eCommerce contexts or any domain outside of customer support automation for online shopping platforms. |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
|
|
The model may struggle with ambiguous or complex queries that don't fall into one of the predefined categories. There may be challenges if a query contains information about a product or service not covered in the training data. Additionally, the model may be biased towards certain types of queries if the dataset used for training wasn't sufficiently diverse. |
|
|
|
|
|
### Recommendations |
|
|
|
|
|
Users should ensure that their query categories are regularly updated to reflect new products, services, or issues. This can improve the model's accuracy and relevance for ongoing customer service tasks. Continuous monitoring and feedback will help in reducing the model's biases and improving its performance. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
To get started with the model, you can use the following code snippet: |
|
|
|
|
|
```python |
|
|
from transformers import T5Tokenizer, T5ForConditionalGeneration |
|
|
|
|
|
# Load pre-trained model and tokenizer |
|
|
model = T5ForConditionalGeneration.from_pretrained('path_to_model') |
|
|
tokenizer = T5Tokenizer.from_pretrained('path_to_tokenizer') |
|
|
|
|
|
# Example usage |
|
|
input_text = "What is the status of my order for a laptop?" |
|
|
inputs = tokenizer(input_text, return_tensors="pt") |
|
|
outputs = model.generate(inputs['input_ids']) |
|
|
decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
print(decoded_output) |
|
|
``` |
|
|
|
|
|
## Uses |
|
|
|
|
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> |
|
|
|
|
|
### Direct Use |
|
|
|
|
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
### Downstream Use [optional] |
|
|
|
|
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
|
|
<!-- This section is meant to convey both technical and sociotechnical limitations. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
### Recommendations |
|
|
|
|
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> |
|
|
|
|
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
Use the code below to get started with the model. |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Data |
|
|
|
|
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
### Training Procedure |
|
|
|
|
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> |
|
|
|
|
|
#### Preprocessing [optional] |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
|
|
|
#### Training Hyperparameters |
|
|
|
|
|
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> |
|
|
|
|
|
#### Speeds, Sizes, Times [optional] |
|
|
|
|
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
<!-- This section describes the evaluation protocols and provides the results. --> |
|
|
|
|
|
### Testing Data, Factors & Metrics |
|
|
|
|
|
#### Testing Data |
|
|
|
|
|
<!-- This should link to a Dataset Card if possible. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
#### Factors |
|
|
|
|
|
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
#### Metrics |
|
|
|
|
|
<!-- These are the evaluation metrics being used, ideally with a description of why. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
### Results |
|
|
|
|
|
The model achieved: |
|
|
|
|
|
- **Accuracy:** 92% for intent classification |
|
|
|
|
|
- **Precision:** 90% for product category classification |
|
|
|
|
|
- **Recall:** 88% for urgency level classification |
|
|
|
|
|
- **F1-Score:** 89% overall across all tasks |
|
|
|
|
|
#### Summary |
|
|
The model shows strong performance in classifying customer queries across multiple categories and levels of urgency. However, there is room for improvement in handling edge cases or complex queries not covered in the training data. |
|
|
|
|
|
|
|
|
## Model Examination [optional] |
|
|
|
|
|
<!-- Relevant interpretability work for the model goes here --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Environmental Impact |
|
|
|
|
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> |
|
|
|
|
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). |
|
|
|
|
|
- **Hardware Type:** [More Information Needed] |
|
|
- **Hours used:** [More Information Needed] |
|
|
- **Cloud Provider:** [More Information Needed] |
|
|
- **Compute Region:** [More Information Needed] |
|
|
- **Carbon Emitted:** [More Information Needed] |
|
|
|
|
|
## Technical Specifications [optional] |
|
|
|
|
|
### Model Architecture and Objective |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
### Compute Infrastructure |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
#### Hardware |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
#### Software |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Citation [optional] |
|
|
|
|
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> |
|
|
|
|
|
**BibTeX:** |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
**APA:** |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Glossary [optional] |
|
|
|
|
|
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## More Information [optional] |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Model Card Authors [optional] |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Model Card Contact |
|
|
|
|
|
[More Information Needed] |
