Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective

TL;DR

This paper introduces the Multi-Perspective Inferrer (MPI), a novel NLI model that reasons from multiple perspectives to better determine sentence relationships, improving accuracy and interpretability.

Contribution

The MPI model employs a routing-by-agreement policy to reason from multiple perspectives and integrates an auxiliary signal for better perspective learning, enhancing NLI performance.

Findings

MPI improves base model performance on SNLI and MultiNLI datasets.

Visualized evidence shows MPI learns interpretable perspectives.

MPI is architecture-free and compatible with BERT.

Abstract

Natural Language Inference (NLI) aims to determine the logic relationships (i.e., entailment, neutral and contradiction) between a pair of premise and hypothesis. Recently, the alignment mechanism effectively helps NLI by capturing the aligned parts (i.e., the similar segments) in the sentence pairs, which imply the perspective of entailment and contradiction. However, these aligned parts will sometimes mislead the judgment of neutral relations. Intuitively, NLI should rely more on multiple perspectives to form a holistic view to eliminate bias. In this paper, we propose the Multi-Perspective Inferrer (MPI), a novel NLI model that reasons relationships from multiple perspectives associated with the three relationships. The MPI determines the perspectives of different parts of the sentences via a routing-by-agreement policy and makes the final decision from a holistic view. Additionally, we introduce an auxiliary supervised signal to ensure the MPI to learn the expected perspectives. Experiments on SNLI and MultiNLI show that 1) the MPI achieves substantial improvements on the base model, which verifies the motivation of multi-perspective inference; 2) visualized evidence verifies that the MPI learns highly interpretable perspectives as expected; 3) more importantly, the MPI is architecture-free and compatible with the powerful BERT.