An Overview of Computational Approaches for Interpretation Analysis

Abstract

It is said that beauty is in the eye of the beholder. But how exactly can we characterize such discrepancies in interpretation? For example, are there any specific features of an image that make person A regard an image as beautiful while person B finds the same image displeasing? Such questions ultimately aim at explaining our individual ways of interpretation, an intention that has been of fundamental importance to the social sciences from the beginning. More recently, advances in computer science brought up two related questions: First, can computational tools be adopted for analyzing ways of interpretation? Second, what if the "beholder" is a computer model, i.e., how can we explain a computer model's point of view? Numerous efforts have been made regarding both of these points, while many existing approaches focus on particular aspects and are still rather disconnected.With this paper, in order to connect these approaches we introduce a theoretical framework for analyzing interpretation, which is applicable to interpretation of both human beings and computer models. We give an overview of relevant computational approaches from various fields, and discuss the most common and promising application areas. The focus of this paper lies on interpretation of text and image data, while many of the presented approaches are applicable to other types of data as well.

Fusion Strategies for Learning User Embeddings with Neural Networks

“…In Table I we see that fusion with multiplicative masks of a moderate embedding size (around 16) works best for prediction. Tensor fusion with similar embedding sizes (16,32) achieves comparable prediction results. Additive masks yield comparatively poor prediction performances, but achieve higher embedding scores.…”

“…Finally, it shall be mentioned that, although we formulated the problem in terms of user ratings, the same modeling can directly be applied to other data such as dialogues. In fact, our chosen approach for learning user embeddings fits the theoretical framework of interpretation analysis proposed by [32], and can be seen as a case of model-based interpretation analysis.…”