An Empirical Comparison of Web Content Extraction Algorithms.

@inproceedings{bevendorff-2023-empirical, author = {Janek Bevendorff and Sanket Gupta and Johannes Kiesel and Benno Stein}, editor = {Hsin-Hsi Chen and Wei-Jou (Edward) Duh and Hen-Hsen Huang and Makoto P. Kato and Josiane Mothe and Barbara Poblete}, title = {{An Empirical Comparison of Web Content Extraction Algorithms}}, booktitle = {{Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023}}, pages = {2594--2603}, publisher = {ACM}, year = {2023}, url = {https://doi.org/10.1145/3539618.3591920}, doi = {https://doi.org/10.1145/3539618.3591920} }