@inproceedings{akbiyik-etal-2025-semantic,
    title = "Semantic Outlier Removal with Embedding Models and {LLM}s",
    author = "Akbiyik, Eren  and
      Almeida, Jo{\~a}o F. M. De  and
      Melis, Rik  and
      Sriram, Ritu  and
      Petrescu, Viviana  and
      Vilhj{\'a}lmsson, Vilhj{\'a}lmur",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-industry.58/",
    pages = "826--835",
    ISBN = "979-8-89176-288-6",
    abstract = "Modern text processing pipelines demand robust methods to remove extraneous content while preserving a document{'}s core message. Traditional approaches{---}such as HTML boilerplate extraction or keyword filters{---}often fail in multilingual settings and struggle with context-sensitive nuances, whereas Large Language Models (LLMs) offer improved quality at high computational cost. We introduce SORE (Semantic Outlier Removal), a cost-effective, transparent method that leverages multilingual sentence embeddings and approximate nearest-neighbor search to identify and excise unwanted text segments. By first identifying core content via metadata embedding and then flagging segments that either closely match predefined outlier groups or deviate significantly from the core, SORE achieves near-LLM extraction precision at a fraction of the cost. Experiments on HTML datasets demonstrate that SORE outperforms structural methods and yield high precision in diverse scenarios. Our system is currently deployed in production, processing millions of documents daily across multiple languages while maintaining both efficiency and accuracy. To facilitate reproducibility and further research, we will publicly release our implementation and evaluation datasets."
}