papers AI Learner
The Github is limit! Click to go to the new site.

Analytical Methods for Interpretable Ultradense Word Embeddings

2019-04-18
Philipp Dufter, Hinrich Schütze

Abstract

Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In this work, we investigate three methods for making word spaces interpretable by rotation: Densifier (Rothe et al., 2016), linear SVMs and DensRay, a new method we propose. While DensRay is very closely related to the Densifier, it can be computed in closed form, is hyperparameter-free and thus more robust than the Densifier. We evaluate the methods on lexicon induction and set-based word analogy and conclude that analytical methods such as DensRay and SVMs are preferable. For word analogy we propose a new method to solve the task which outperforms the previous state of the art by large margins.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.08654

PDF

http://arxiv.org/pdf/1904.08654


Comments

Content