RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees

10/31/2022
by   Tengxiao Liu, et al.
0

Interpreting the reasoning process from questions to answers poses a challenge in approaching explainable QA. A recently proposed structured reasoning format, entailment tree, manages to offer explicit logical deductions with entailment steps in a tree structure. To generate entailment trees, prior single pass sequence-to-sequence models lack visible internal decision probability, while stepwise approaches are supervised with extracted single step data and cannot model the tree as a whole. In this work, we propose RLET, a Reinforcement Learning based Entailment Tree generation framework, which is trained utilising the cumulative signals across the whole tree. RLET iteratively performs single step reasoning with sentence selection and deduction generation modules, from which the training signal is accumulated across the tree with elaborately designed aligned reward function that is consistent with the evaluation. To the best of our knowledge, we are the first to introduce RL into the entailment tree generation task. Experiments on three settings of the EntailmentBank dataset demonstrate the strength of using RL framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/05/2022

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

Knowing the reasoning chains from knowledge to the predicted answers can...
research
05/18/2022

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner

Large language models have achieved high performance on various question...
research
04/17/2021

Explaining Answers with Entailment Trees

Our goal, in the context of open-domain textual question-answering (QA),...
research
08/02/2022

Active entailment encoding for explanation tree construction using parsimonious generation of hard negatives

Entailment trees have been proposed to simulate the human reasoning proc...
research
05/24/2022

Policy Compliance Detection via Expression Tree Inference

Policy Compliance Detection (PCD) is a task we encounter when reasoning ...
research
12/16/2021

QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization

Factual consistency is an essential quality of text summarization models...
research
02/23/2018

Can Neural Networks Understand Logical Entailment?

We introduce a new dataset of logical entailments for the purpose of mea...

Please sign up or login with your details

Forgot password? Click here to reset