2025-01-14-tan25b.md

title	Improve Diverse Commonsense Generation by Enhancing Subgraphs
booktitle	Proceedings of the 16th Asian Conference on Machine Learning
year	2025
volume	260
series	Proceedings of Machine Learning Research
month	0
publisher	PMLR
pdf	https://raw.githubusercontent.com/mlresearch/v260/main/assets/tan25b/tan25b.pdf
url	https://proceedings.mlr.press/v260/tan25b.html
openreview	MNFKsF4RiF
abstract	Commonsense reasoning (CSR) requires rationale beyond the explicit knowledge mentioned in the context. Many existing methods use knowledge graphs (KGs) to generate rationale as additional evidence for CSR. However, rationale extracted from KGs (e.g., ConceptNet) often includes irrelevant information, which easily introduces noise and affects the evidential quality generated. Similar to brainstorming to generate diverse ideas, we introduce a synonym expansion method to expand input concepts, ultimately constructing a task relevant knowledge subgraph. Additionally, we propose a pruning model that learns to score and prune the knowledge subgraph, removing parts that are not directly related to the input context. The proposed method improves the quality and diversity of rationale, which benefits generative commonsense reasoning tasks. Experiments on two datasets validated the effectiveness of our method, which demonstrates comparable performance with existing methods.
layout	inproceedings
issn	2640-3498
id	tan25b
tex_title	Improve Diverse Commonsense Generation by Enhancing Subgraphs
firstpage	750
lastpage	764
page	750-764
order	750
cycles	false
bibtex_editor	Nguyen, Vu and Lin, Hsuan-Tien
editor	given family Vu Nguyen given family Hsuan-Tien Lin
bibtex_author	Tan, Jianman and Yang, Shuo
author	given family Jianman Tan given family Shuo Yang
date	2025-01-14
address
container-title	Proceedings of the 16th Asian Conference on Machine Learning
genre	inproceedings
issued	date-parts 2025 1 14
extras