Class-based Prediction Errors to Categorize Text with Out-of-vocabulary WordsDownload PDF

21 Jun 2024 (modified: 17 Feb 2017)ICLR 2017 workshop submissionReaders: Everyone
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. To better deal with these issues, we propose to use 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 4-11%.
TL;DR: Using class-based prediction errors is a promising strategy to classify text with out-of-vocabulary words
Keywords: Natural language processing, Applications
5 Replies