FE-TCM: Filter-Enhanced Transformer Click Model for Web Search

Constructing click models and extracting implicit relevance feedback information from interaction between users and search engines are very important for improving the ranking of search results. Neural networks are effective for modeling users' click behavior, and we propose a novel Filter-Enhanced Transformer Click Model (FE-TCM) for web search. The model uses the powerful Transformer model as the backbone network for feature extraction and innovatively add a filter layer. Firstly, in order to reduce the influence of noise on user behavior data, we use the learnable filters to filter the log noise. Secondly, following the examination hypothesis, we model the attraction estimator and examination predictor respectively to output attractiveness scores and examination probabilities. A novel transformer model is used to learn the deeper representation among different features. Finally, we apply the different combination functions to integrate attractiveness scores and examination probabilities into the click prediction. From our experiments on two real-world session datasets, it is proved that FE-TCM outperforms the existing click models for the click prediction.