METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation

TL;DR

METGEN is a modular framework that generates more reliable and valid entailment trees for explainable question answering by controlling reasoning steps with specialized modules.

Contribution

It introduces a module-based approach with a reasoning controller to improve entailment tree generation in explainable QA systems.

Findings

Outperforms previous models on standard benchmarks.

Uses only 9% of the parameters of prior models.

Generates more reliable and valid reasoning steps.

Abstract

Knowing the reasoning chains from knowledge to the predicted answers can help construct an explainable question answering (QA) system. Advances on QA explanation propose to explain the answers with entailment trees composed of multiple entailment steps. While current work proposes to generate entailment trees with end-to-end generative models, the steps in the generated trees are not constrained and could be unreliable. In this paper, we propose METGEN, a Module-based Entailment Tree GENeration framework that has multiple modules and a reasoning controller. Given a question and several supporting knowledge, METGEN can iteratively generate the entailment tree by conducting single-step entailment with separate modules and selecting the reasoning flow with the controller. As each module is guided to perform a specific type of entailment reasoning, the steps generated by METGEN are more reliable and valid. Experiment results on the standard benchmark show that METGEN can outperform previous state-of-the-art models with only 9% of the parameters.