Towards Controllable Natural Language Inference through Lexical Inference Types

TL;DR

This paper introduces a controlled natural language inference model that uses lexical inference types based on AMR graphs to improve explainability and control in multi-hop inference, supported by a new annotated dataset.

Contribution

It proposes a novel T5-based architecture with a latent sentence representation conditioned on lexical inference types for explainable multi-premise inference.

Findings

Inference typing at the T5 bottleneck improves control over generated conclusions.

The model generates more grounded and explainable inference steps.

The new dataset supports training and evaluation of controlled inference models.

Abstract

Explainable natural language inference aims to provide a mechanism to produce explanatory (abductive) inference chains which ground claims to their supporting premises. A recent corpus called EntailmentBank strives to advance this task by explaining the answer to a question using an entailment tree \cite{dalvi2021explaining}. They employ the T5 model to directly generate the tree, which can explain how the answer is inferred. However, it lacks the ability to explain and control the generation of intermediate steps, which is crucial for the multi-hop inference process. % One recent corpus, EntailmentBank, aims to push this task forward by explaining an answer to a question according to an entailment tree \cite{dalvi2021explaining}. They employ T5 to generate the tree directly, which can explain how the answer is inferred but cannot explain how the intermediate is generated, which is essential to the multi-hop inference process. In this work, we focus on proposing a controlled natural language inference architecture for multi-premise explanatory inference. To improve control and enable explanatory analysis over the generation, we define lexical inference types based on Abstract Meaning Representation (AMR) graph and modify the architecture of T5 to learn a latent sentence representation (T5 bottleneck) conditioned on said type information. We also deliver a dataset of approximately 5000 annotated explanatory inference steps, with well-grounded lexical-symbolic operations. Experimental results indicate that the inference typing induced at the T5 bottleneck can help T5 to generate a conclusion under explicit control.