PROMPT LEARNING ON ABDUCTIVE COMMONSENSE REASONING

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "PROMPT LEARNING ON ABDUCTIVE COMMONSENSE REASONING"

By

Mr. Chun Kit CHAN


Abstract:

Abduction has long been seen as crucial for narrative comprehension and
reasoning about everyday situations. The abductive natural language inference
(aNLI) 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 not been
well exploited in the previous works on this task. In this study, we propose a
prompt tuning model a-PACE, which takes self-consistency and inter-sentential
coherence into consideration. Besides, we propose a general selfconsistency
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 a-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:                   Friday, 28 July 2023

Time:                   2:00pm - 4:00pm

Venue:                  Room 5501
                        lifts 25/26

Committee Members:      Dr. Yangqiu Song (Supervisor)
                        Dr. Dan Xu (Chairperson)
                        Dr. Long Chen


**** ALL are Welcome ****