Hy-NLI: a Hybrid system for Natural Language Inference

Proceedings of the 28th International Conference on Computational Linguistics, pages 519–529 Barcelona, Spain (Online), December 8-13, 2020 519 Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution Benedikt Boenninghoff,1 Steffen Zeiler,1 Robert M. Nickel,2 Dorothea Kolossa1 1Cognitive Signal Processing Group, Ruhr University Bochum, Germany 2Department of Electrical and Computer Engineering, Bucknell University, Lewisburg, PA, USA {benedikt.boenninghoff, dorothea.kolossa, steffen.zeiler}@rub.de rmn009@bucknell.edu Abstract Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. Variational autoencoders (VAEs) have had tremendous success in learning latent representations. However, existing VAEs are currently still bound by limitations imposed by the assumed Gaussianity of the underlying probability distributions in the latent space. In this work, we are extending a VAE with an embedded Gaussian mixture model to a Student-t mixture model, which allows for an independent control of the “heaviness” of the respective tails of the implied probability densities. Experiments over an Amazon review dataset indicate superior performance of the proposed method. 1 Introduction doc 1 doc 2 doc 4doc 3 doc 6doc 5 doc 7 author 1 author 2 author 3 Encoder Decoder Observation space Hidden space Figure 1: Non-linear observation model for authorship analysis. Supervised authorship attribution traditionally refers to the task of analyzing the linguistic patterns of a text in order to determine who, from a finite set of enrolled authors, has written a document of unknown authorship. Nowadays, the focus of this closed-set scenario has shifted from lit- erary to social media authorship attribution, where meth- ods have been developed to deal with large-scale datasets of small-sized online texts. Examples are provided by the work of (Rocha et al., 2017), (Boenninghoff et al., 2019a), (Theophilo et al., 2019), and (Tschuggnall et al., 2019). The ADHOMINEM system proposed by (Boenninghoff et al., 2019b) is a linguistically motivated deep learning topology that can be seen as a feature extractor for such a tasks. The original ADHOMINEM system is trained on a large dataset of Amazon reviews1, each written by one of 784, 649 distinct authors. The key aspect of ADHOMINEM is that it is not designed to recognize authors but, instead, to recognize a difference in authorship between two given texts. As such, the system produces internal neural features, i.e. observation space features (see Fig. 1), that do not directly represent authorship but rather the stylistic characteristics that distinguish authorship. Since ADHOMINEM is trained with a large number of authors and since the space of writing style variations across authors is generally almost as big as the space of writing style variations itself, it can be argued that features produced by ADHOMINEM can serve as a proxy representation for writing style variations in general. The features produced by ADHOMINEM, therefore, have favorable properties for a variety of writing-style-based …

Content truncated to 500 words