Autoregressive Reasoning over Chains of Facts with Transformers

12/17/2020
by   Ruben Cartuyvels, et al.
0

This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources of evidence or facts for multi-hop reasoning becomes increasingly hard when the number of sources needed to make an inference grows. Our algorithm copes with this by decomposing the selection of facts from a corpus autoregressively, conditioning the next iteration on previously selected facts. This allows us to use a pairwise learning-to-rank loss. We validate our method on datasets of the TextGraphs 2019 and 2020 Shared Tasks for explanation regeneration. Existing work on this task either evaluates facts in isolation or artificially limits the possible chains of facts, thus limiting multi-hop inference. We demonstrate that our algorithm, when used with a pre-trained transformer model, outperforms the previous state-of-the-art in terms of precision, training time and inference efficiency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/17/2021

Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts

Language-enabled AI systems can answer complex, multi-hop questions to h...
research
09/30/2020

Explainable Natural Language Reasoning via Conceptual Unification

This paper presents an abductive framework for multi-hop and interpretab...
research
11/02/2020

Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps

A multi-hop question answering (QA) dataset aims to test reasoning and i...
research
06/07/2019

Compositional Questions Do Not Necessitate Multi-hop Reasoning

Multi-hop reading comprehension (RC) questions are challenging because t...
research
05/29/2018

Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?

Question Answering for complex questions is often modeled as a graph con...
research
09/19/2019

ASU at TextGraphs 2019 Shared Task: Explanation ReGeneration using Language Models and Iterative Re-Ranking

In this work we describe the system from Natural Language Processing gro...
research
08/22/2015

Towards Neural Network-based Reasoning

We propose Neural Reasoner, a framework for neural network-based reasoni...

Please sign up or login with your details

Forgot password? Click here to reset