Natural Language Inference over Interaction Space
This addresses the problem of logical relationship inference between sentence pairs for NLP researchers, representing a strong incremental improvement.
The paper tackles the Natural Language Inference (NLI) task by introducing the Densely Interactive Inference Network (DIIN), which hierarchically extracts semantic features from interaction space. It achieves state-of-the-art performance, including a greater than 20% error reduction on the MultiNLI dataset compared to the strongest published system.
Natural Language Inference (NLI) task requires an agent to determine the logical relationship between a natural language premise and a natural language hypothesis. We introduce Interactive Inference Network (IIN), a novel class of neural network architectures that is able to achieve high-level understanding of the sentence pair by hierarchically extracting semantic features from interaction space. We show that an interaction tensor (attention weight) contains semantic information to solve natural language inference, and a denser interaction tensor contains richer semantic information. One instance of such architecture, Densely Interactive Inference Network (DIIN), demonstrates the state-of-the-art performance on large scale NLI copora and large-scale NLI alike corpus. It's noteworthy that DIIN achieve a greater than 20% error reduction on the challenging Multi-Genre NLI (MultiNLI) dataset with respect to the strongest published system.