COGEN: Abductive Commonsense Language Generation
Rohola Zandie, Diwanshu Shekhar, Mohammad H. Mahoor · 2023
Reasoning is one of the most important elements in achieving Artificial General Intelligence (AGI), specifically when it comes to Abductive and counterfactual reasoning.In order to introduce these capabilities of reasoning in Natural Language Processing (NLP) models, there have been recent advances toward training NLP models to better perform on two main tasks -Abductive Natural Language Inference (αNLI) and Abductive Natural Language Generation Task (αNLG).This paper proposes CO-GEN, a model for both αNLI and αNLG tasks that employs a novel approach of combining the temporal commonsense reasoning for each observation (before and after a real hypothesis) from pre-trained models with entailment-based filtering for training.Additionally, we use stateof-the-art semantic entailment to filter out the contradictory hypothesis during the inference.Our experimental results show that COGEN outperforms current models and set a new state of the art in regards to αNLI and αNLG tasks.We make the source code of the COGEN model publicly available for reproducibility and to facilitate relevant future research.