Natural Language Inference over Interaction Space

ICLR 2018  ·  Yichen Gong, Heng Luo, Jian Zhang ·

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.

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Paraphrase Identification Quora Question Pairs DIIN Accuracy 89.06 # 12
Natural Language Inference SNLI 448D Densely Interactive Inference Network (DIIN, code) Ensemble % Test Accuracy 88.9 # 20
% Train Accuracy 92.3 # 30
Parameters 17m # 3
Natural Language Inference SNLI 448D Densely Interactive Inference Network (DIIN, code) % Test Accuracy 88.0 # 36
% Train Accuracy 91.2 # 36
Parameters 4.4m # 3

Methods


No methods listed for this paper. Add relevant methods here