Prompt learning on abductive commonsense reasoning

Abstract

Abduction has long been seen as crucial for narrative comprehension and reasoning about everyday situations. The abductive natural language inference (αNLI) task has been proposed, and this narrative text-based task aims to infer the most plausible hypothesis from the candidates given two observations. However, the inter-sentential coherence and the model consistency have yet to be well exploited in the previous works on this task. In this study, we propose a prompt tuning model α-PACE, which takes self-consistency and inter-sentential coherence into consideration. Besides, we propose a general self-consistency framework that considers various narrative sequences (e.g., linear narrative and reverse chronology) for guiding the pre-trained language model in understanding the narrative context of input. We conduct extensive experiments and thorough ablation studies to illustrate the necessity and effectiveness of α-PACE. The performance of our method shows significant improvement against extensive competitive baselines in the full data and few-shot settings. Finally, we validate the interpretability of neuralized continuous prompts by providing qualitative and quantitative analysis.

Date of Award	2023
Original language	English
Awarding Institution	The Hong Kong University of Science and Technology
Supervisor	Yangqiu SONG (Supervisor)