Hyperbolic sentence representations for solving Textual Entailment

TL;DR

This work uses the Poincare ball to embed sentences with the goal of proving how hyperbolic spaces can be used for solving Textual Entailment, and develops two additional datasets used for evaluating textual entailment.

Abstract

Hyperbolic spaces have proven to be suitable for modeling data of hierarchical nature. As such we use the Poincare ball to embed sentences with the goal of proving how hyperbolic spaces can be used for solving Textual Entailment. To this end, apart from the standard datasets used for evaluating textual entailment, we developed two additional datasets. We evaluate against baselines of various backgrounds, including LSTMs, Order Embeddings and Euclidean Averaging, which comes as a natural counterpart to representing sentences into the Euclidean space. We consistently outperform the baselines on the SICK dataset and are second only to Order Embeddings on the SNLI dataset, for the binary classification version of the entailment task.

Figures (15)

• Figure 1: RNN visualization rnn_blog
• Figure 2: General architecture for Textual Entailment nli_learning_scheme
• Figure 3: Tangent space of a point image_tangent_space
• Figure 4: Parallel postulate doesn't hold in the hyperbolic geometry img_parallel_postulate
• Figure 5: Poincare distance proximity poincare_dist_images

Theorems & Definitions (1)

• proof