COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering

TL;DR

COSMO is a novel conditional sequence-to-sequence mixture model that dynamically generates context-dependent knowledge graphs to improve zero-shot commonsense question answering, outperforming existing models.

Contribution

The paper introduces COSMO, a new model that enables dynamic, diverse knowledge generation for zero-shot commonsense reasoning, addressing limitations of prior approaches.

Findings

Up to +5.2% improvement over state-of-the-art models.

Effective generation of context-dependent knowledge graphs.

Enhanced ability to perform zero-shot commonsense reasoning.

Abstract

Commonsense reasoning refers to the ability of evaluating a social situation and acting accordingly. Identification of the implicit causes and effects of a social context is the driving capability which can enable machines to perform commonsense reasoning. The dynamic world of social interactions requires context-dependent on-demand systems to infer such underlying information. However, current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation, mostly due to incapability of identifying a diverse range of implicit social relations. Hence they fail to estimate the correct reasoning path. In this paper, we present Conditional SEQ2SEQ-based Mixture model (COSMO), which provides us with the capabilities of dynamic and diverse content generation. We use COSMO to generate context-dependent clauses, which form a dynamic Knowledge Graph (KG) on-the-fly for commonsense reasoning. To show the adaptability of our model to context-dependant knowledge generation, we address the task of zero-shot commonsense question answering. The empirical results indicate an improvement of up to +5.2% over the state-of-the-art models.