Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation. In this paper, we develop a novel method to learn a heavy-tailed embedding with desirable regularity properties regarding the distributional tails, which allows to analyze the points far away from the distribution bulk using the framework of multivariate extreme value theory. In particular, a classifier dedicated to the tails of the proposed embedding is obtained which exhibits a scale invariance property exploited in a novel text generation method for label preserving dataset augmentation. Experiments on synthetic and real text data show the relevance of the proposed framework and confirm that this method generates meaningful sentences with controllable attribute, e. g. positive or negative sentiments.

Authors

• Hamid Jalalzai
• Pierre Colombo Université Paris-Saclay CentraleSupelec Equal, Paris MICS
• Chloé Clavel LTCI, Télécom Paris, Institut Polytechnique de Paris
• Eric Gaussier
• Giovanna Varni
• Emmanuel Vignon
• Anne Sabourin

Keywords

No keywords are indexed for this paper.