Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach

by   Chao Zhao, et al.

Pre-trained models (PTMs) have lead to great improvements in natural language generation (NLG). However, it is still unclear how much commonsense knowledge they possess. With the goal of evaluating commonsense knowledge of NLG models, recent work has proposed the problem of generative commonsense reasoning, e.g., to compose a logical sentence given a set of unordered concepts. Existing approaches to this problem hypothesize that PTMs lack sufficient parametric knowledge for this task, which can be overcome by introducing external knowledge or task-specific pre-training objectives. Different from this trend, we argue that PTM's inherent ability for generative commonsense reasoning is underestimated due to the order-agnostic property of its input. In particular, we hypothesize that the order of the input concepts can affect the PTM's ability to utilize its commonsense knowledge. To this end, we propose a pre-ordering approach to elaborately manipulate the order of the given concepts before generation. Experiments show that our approach can outperform the more sophisticated models that have access to a lot of external data and resources.


page 1

page 2

page 3

page 4


Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey

While commonsense knowledge acquisition and reasoning has traditionally ...

KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning

Generative commonsense reasoning which aims to empower machines to gener...

Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph

Despite the success of generative pre-trained language models on a serie...

Improving Question Answering by Commonsense-Based Pre-Training

Although neural network approaches achieve remarkable success on a varie...

Situated Structure Learning of a Bayesian Logic Network for Commonsense Reasoning

This paper details the implementation of an algorithm for automatically ...

Logical Semantics and Commonsense Knowledge: Where Did we Go Wrong, and How to Go Forward, Again

We argue that logical semantics might have faltered due to its failure i...

No Adjective Ordering Mystery, and No Raven Paradox, Just an Ontological Mishap

In the concluding remarks of Ontological Promiscuity Hobbs (1985) made w...