AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913422738718720 |
|---|---|
| author | Guo, Shouchang Damani, Sonam Chang, Keng-hao |
| author_facet | Guo, Shouchang Damani, Sonam Chang, Keng-hao |
| contents | Ads relevance models are crucial in determining the relevance between user search queries and ad offers, often framed as a classification problem. The complexity of modeling increases significantly with multiple ad types and varying scenarios that exhibit both similarities and differences. In this work, we introduce a novel multi-faceted attention model that performs task aware feature combination and cross task interaction modeling. Our technique formulates the feature combination problem as "language" modeling with auto-regressive attentions across both feature and task dimensions. Specifically, we introduce a new dimension of task ID encoding for task representations, thereby enabling precise relevance modeling across diverse ad scenarios with substantial improvement in generality capability for unseen tasks. We demonstrate that our model not only effectively handles the increased computational and maintenance demands as scenarios proliferate, but also outperforms generalized DNN models and even task-specific models across a spectrum of ad applications using a single unified model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06549 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance Guo, Shouchang Damani, Sonam Chang, Keng-hao Information Retrieval Artificial Intelligence Computation and Language Machine Learning Ads relevance models are crucial in determining the relevance between user search queries and ad offers, often framed as a classification problem. The complexity of modeling increases significantly with multiple ad types and varying scenarios that exhibit both similarities and differences. In this work, we introduce a novel multi-faceted attention model that performs task aware feature combination and cross task interaction modeling. Our technique formulates the feature combination problem as "language" modeling with auto-regressive attentions across both feature and task dimensions. Specifically, we introduce a new dimension of task ID encoding for task representations, thereby enabling precise relevance modeling across diverse ad scenarios with substantial improvement in generality capability for unseen tasks. We demonstrate that our model not only effectively handles the increased computational and maintenance demands as scenarios proliferate, but also outperforms generalized DNN models and even task-specific models across a spectrum of ad applications using a single unified model. |
| title | AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2407.06549 |