@proceedings {1953, title = {Class-based Prediction Errors to Categorize Text with Out-of-vocabulary Words}, series = {ALW1{\textquoteright}17}, year = {2017}, address = {Vancouver, Canada}, abstract = {

Common approaches to text categorization essentially rely either on n-gram counts or on word embeddings. This presents important difficulties in highly dynamic or quickly-interacting environments, where the appearance of new words and/or varied misspellings is the norm. A paradigmatic example of this situation is abusive online behavior, with social networks and media platforms struggling to effectively combat uncommon or non-blacklisted hate words. To better deal with these issues in those fast-paced environments, we propose using the error signal of class-based language models as input to text classification algorithms. In particular, we train a next-character prediction model for any given class, and then exploit the error of such class-based models to inform a neural network classifier. This way, we shift from the ability to describe seen documents to the ability to predict unseen content. Preliminary studies using out-of-vocabulary splits from abusive tweet data show promising results, outperforming competitive text categorization strategies by 4{\textendash}11\%.

}, author = {Joan Serr{\`a} and Ilias Leontiadis and Dimitris Spathis and Gianluca Stringhini and Jeremy Blackburn and Athena Vakali} }