Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917786560757760 |
|---|---|
| author | Li, Yuchen Xiong, Haoyi Kong, Linghe Bian, Jiang Wang, Shuaiqiang Chen, Guihai Yin, Dawei |
| author_facet | Li, Yuchen Xiong, Haoyi Kong, Linghe Bian, Jiang Wang, Shuaiqiang Chen, Guihai Yin, Dawei |
| contents | Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries. However, traditional LTR models encounter two principal obstacles that lead to suboptimal performance: (1) the lack of well-annotated query-webpage pairs with ranking scores covering a diverse range of search query popularities, which hampers their ability to address queries across the popularity spectrum, and (2) inadequately trained models that fail to induce generalized representations for LTR, resulting in overfitting. To address these challenges, we propose a \emph{\uline{G}enerative \uline{S}emi-\uline{S}upervised \uline{P}re-trained} (GS2P) LTR model. We conduct extensive offline experiments on both a publicly available dataset and a real-world dataset collected from a large-scale search engine. Furthermore, we deploy GS2P in a large-scale web search engine with realistic traffic, where we observe significant improvements in the real-world application. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16594 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract) Li, Yuchen Xiong, Haoyi Kong, Linghe Bian, Jiang Wang, Shuaiqiang Chen, Guihai Yin, Dawei Information Retrieval Machine Learning Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries. However, traditional LTR models encounter two principal obstacles that lead to suboptimal performance: (1) the lack of well-annotated query-webpage pairs with ranking scores covering a diverse range of search query popularities, which hampers their ability to address queries across the popularity spectrum, and (2) inadequately trained models that fail to induce generalized representations for LTR, resulting in overfitting. To address these challenges, we propose a \emph{\uline{G}enerative \uline{S}emi-\uline{S}upervised \uline{P}re-trained} (GS2P) LTR model. We conduct extensive offline experiments on both a publicly available dataset and a real-world dataset collected from a large-scale search engine. Furthermore, we deploy GS2P in a large-scale web search engine with realistic traffic, where we observe significant improvements in the real-world application. |
| title | Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract) |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2409.16594 |