--- library_name: transformers tags: - e-commerce - query-generation license: mit datasets: - smartcat/Amazon-2023-GenQ language: - en metrics: - rouge base_model: - BeIR/query-gen-msmarco-t5-base-v1 pipeline_tag: text2text-generation --- # Model Card for T5-GenQ-TDE-v1 🤖 ✨ 🔍 Generate precise, realistic user-focused search queries from product text 🛒 🚀 📊 ### Model Description - **Model Name:** Fine-Tuned Query-Generation Model - **Model type:** Text-to-Text Transformer - **Finetuned from model:** [BeIR/query-gen-msmarco-t5-base-v1](https://huggingface.co/BeIR/query-gen-msmarco-t5-base-v1) - **Dataset**: [smartcat/Amazon-2023-GenQ](https://huggingface.co/datasets/smartcat/Amazon-2023-GenQ) - **Primary Use Case**: Generating accurate and relevant search queries from item descriptions - **Repository:** [smartcat-labs/product2query](https://github.com/smartcat-labs/product2query) ### Model variations
Model | ROUGE-1 | ROUGE-2 | ROUGE-L | ROUGE-Lsum |
---|---|---|---|---|
T5-GenQ-T-v1 | 75.2151 | 54.8735 | 74.5142 | 74.5262 |
T5-GenQ-TD-v1 | 78.2570 | 58.9586 | 77.5308 | 77.5466 |
T5-GenQ-TDE-v1 | 76.9075 | 57.0980 | 76.1464 | 76.1502 |
T5-GenQ-TDC-v1 (best) | 80.0754 | 61.5974 | 79.3557 | 79.3427 |
Model | ROUGE-1 | ROUGE-2 | ROUGE-L | ROUGE-Lsum |
---|---|---|---|---|
T5-GenQ-TDE-v1 | 74.71 | 54.31 | 74.06 | 74.06 |
query-gen-msmarco-t5-base-v1 | 37.63 | 17.40 | 36.69 | 36.69 |
Input Text | Target Query | Before Fine-tuning | After Fine-tuning |
---|---|---|---|
KIDSCOOL SPACE Baby Denim Overall,Hooded Little Kid Jean Jumper | KIDSCOOL SPACE Baby Denim Overall | what is kidscool space denim | baby denim overalls |
NCAA Mens Long Sleeve Shirt Arm Team Show your Mountaineers pride with this West Virginia long sleeve shirt. Its soft cotton material and unique graphics make this a great addition to any West Virginia apparel collection. Features: -100% cotton -Ribbed and double stitched collar and sleeves -Officially licensed West Virginia University long sleeve shirt | West Virginia long sleeve shirt | wvu long sleeve shirt | West Virginia long sleeve shirt |
The Body Shop Mattifying Lotion (Vegan), Tea Tree, 1.69 Fl Oz Product Description Made with community trade tea tree oil, The Body Shop's Tea Tree Mattifying Lotion provides lightweight hydration, helps tackles excess oil and visibly reduces the appearance of blemishes, revealing a clearer looking, mattifed finish. 100 percent vegan, suitable for blemish prone skin. From the Manufacturer Made with Community Trade tea tree oil, The Body Shop's Tea Tree Mattifying Lotion provides lightweight hydration, helps tackles excess oil and visibly reduces the appearance of blemishes, revealing a clearer-looking, mattifed finish. 100% vegan, suitable for blemish-prone skin. Paraben-free. Gluten-free. 100% Vegan. | Tea Tree Mattifying Lotion | what is body shop tea tree lotion | vegan matte lotion |
Epoch | Step | Loss | Grad Norm | Learning Rate | Eval Loss | ROUGE-1 | ROUGE-2 | ROUGE-L | ROUGE-Lsum |
---|---|---|---|---|---|---|---|---|---|
1.0 | 8569 | 0.7955 | 2.9784 | 4.9e-05 | 0.6501 | 75.3001 | 55.0195 | 74.6632 | 74.6678 |
2.0 | 17138 | 0.6595 | 3.2943 | 4.2e-05 | 0.6293 | 76.2210 | 56.2050 | 75.5728 | 75.5670 |
3.0 | 25707 | 0.5982 | 4.0392 | 3.5e-05 | 0.6207 | 76.5493 | 56.7006 | 75.8775 | 75.8796 |
4.0 | 34276 | 0.5552 | 2.8237 | 2.8e-05 | 0.6267 | 76.5433 | 56.7025 | 75.8319 | 75.8343 |
5.0 | 42845 | 0.5225 | 2.7701 | 2.1e-05 | 0.6303 | 76.7192 | 56.9090 | 75.9884 | 75.9972 |
6.0 | 51414 | 0.4974 | 3.1344 | 1.4e-05 | 0.6316 | 76.8851 | 57.1349 | 76.1420 | 76.1484 |
7.0 | 59983 | 0.4798 | 3.5027 | 7e-06 | 0.6355 | 76.8884 | 57.1055 | 76.1433 | 76.1501 |
8.0 | 68552 | 0.4674 | 4.5172 | 0.0 | 0.6408 | 76.9075 | 57.0980 | 76.1464 | 76.1502 |
![]() |
```checkpoint-68552``` (T5-GenQ-TDE-v1) outperforms ```query-gen-msmarco-t5-base-v1``` across all ROUGE metrics. The most significant difference is in ROUGE-2, where ```checkpoint-68552``` scores 54.32% vs. 17.40% for the baseline model. |
![]() |
```checkpoint-68552``` (T5-GenQ-TDE-v1) peaks near 100%, showing strong text overlap. ```query-gen-msmarco-t5-base-v1``` has a wider distribution, with peaks in the low to mid-score range (10-40%), indicating greater variability but lower precision. ROUGE-2 has a high density at 0% for the baseline model, meaning many outputs lack bigram overlap. |
![]() |
```checkpoint-68552``` (T5-GenQ-TDE-v1, blue) trends toward higher ROUGE scores, with a peak at 100%. ```query-gen-msmarco-t5-base-v1``` (orange) has more low-score peaks, especially in ROUGE-2, reinforcing its lower precision. These histograms confirm ```checkpoint-68552``` consistently generates more accurate text. |
![]() |
Stable ROUGE scores (Sizes 3-9): All metrics remain consistently high. Score spike at 2 words: Indicates better alignment for short phrases, followed by stability. Score differences remain near zero for most sizes, meaning consistent model performance across phrase lengths. |
![]() |
This histogram visualizes the distribution of cosine similarity scores, which measure the semantic similarity between paired texts (generated query and target query). A strong peak near 1.0 suggests most pairs are highly semantically similar. Low similarity scores (0.0–0.4) are rare, meaning the dataset contains mostly closely related text pairs. |
![]() |
Higher similarity → Higher ROUGE scores, indicating strong correlation. ROUGE-1 & ROUGE-L show the strongest alignment, while ROUGE-2 has more variation. Some low-similarity outliers still achieve moderate ROUGE scores, suggesting surface-level overlap without deep semantic alignment. |