Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset
This work addresses the need for efficient relevance ranking in web search engines, though it is incremental as it adapts existing transformer methods to a specific domain.
The authors tackled the challenge of using computationally expensive BERT models for real-time web search ranking by deploying a siamese BERT-based architecture, which improved production performance by over 3% in a commercial search engine.
Web search engines focus on serving highly relevant results within hundreds of milliseconds. Pre-trained language transformer models such as BERT are therefore hard to use in this scenario due to their high computational demands. We present our real-time approach to the document ranking problem leveraging a BERT-based siamese architecture. The model is already deployed in a commercial search engine and it improves production performance by more than 3%. For further research and evaluation, we release DaReCzech, a unique data set of 1.6 million Czech user query-document pairs with manually assigned relevance levels. We also release Small-E-Czech, an Electra-small language model pre-trained on a large Czech corpus. We believe this data will support endeavours both of search relevance and multilingual-focused research communities.