@inproceedings{falco-etal-2012-kitten, title = "{K}itten: a tool for normalizing {HTML} and extracting its textual content", author = "Falco, Mathieu-Henri and Moriceau, V{\'e}ronique and Vilnat, Anne", editor = "Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u{g}}an, Mehmet U{\u{g}}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios", booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}`12)", month = may, year = "2012", address = "Istanbul, Turkey", publisher = "European Language Resources Association (ELRA)", url = "https://aclanthology.org/L12-1250/", pages = "2261--2267" }