{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/siamese-bert-based-model-for-web-search","title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","arxiv_id":"2112.01810","date":"2021-12-03","proceeding":null,"authors":["Matěj Kocián","Jakub Náplava","Daniel Štancl","Vladimír Kadlec"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2112.01810v1","url_pdf":"https://arxiv.org/pdf/2112.01810v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"siamese-bert-based-model-for-web-search","repo_url":"https://github.com/seznam/dareczech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-ranking","task_name":"Document Ranking"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"small-language-model","task_name":"Small Language Model"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"dareczech","name":"DaReCzech","full_name":"Dataset for text relevance ranking in Czech"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-ranking-on-dareczech","task":"Document Ranking","dataset":"DaReCzech","model":"Query-doc RobeCzech (Roberta-base)","rank_in_archive_order":1,"of":3,"metrics":{"P@10":"46.73"},"uses_additional_data":false},{"leaderboard":"/sota/document-ranking-on-dareczech","task":"Document Ranking","dataset":"DaReCzech","model":"Query-doc Small-E-Czech (Electra-small)","rank_in_archive_order":2,"of":3,"metrics":{"P@10":"46.30"},"uses_additional_data":false},{"leaderboard":"/sota/document-ranking-on-dareczech","task":"Document Ranking","dataset":"DaReCzech","model":"Siamese Small-E-Czech (Electra-small)","rank_in_archive_order":3,"of":3,"metrics":{"P@10":"45.26"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}