mlsanityData to 14 Oct 2026

Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset

arXiv 2112.01810 ↗First posted 3 Dec 2021cs.IR cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 15 of its 29 references that are in the map. First posted on arXiv 3 Dec 2021.

Builds on

15 of 29 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  9. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  10. 2018Model compression via distillation and quantizationcited by 289
  11. 201975 Languages, 1 Model: Parsing Universal Dependencies Universallycited by 90
  12. 2020RepBERT: Contextualized Text Embeddings for First-Stage Retrievalcited by 46
3 more
  1. 2020ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Searchcited by 34
  2. 2021RobeCzech: Czech RoBERTa, a monolingual contextualized language representation modelcited by 33
  3. 2020TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrievalcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2022Czech Dataset for Cross-lingual Subjectivity Classificationcited by 5
  2. 2023Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Modelcited by 5
  3. 2025Czech Dataset for Complex Aspect-Based Sentiment Analysis Taskscited by 4
  4. 2023Some Like It Small: Czech Semantic Embedding Models for Industry Applicationscited by 3
  5. 2024CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Rankingcited by 2
  6. 2024A Comparative Study of Text Retrieval Models on DaReCzechcited by 0
  7. 2026CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documentscited by 0