Improve Diverse Commonsense Generation by Enhancing Subgraphs

Jianman Tan, Shuo Yang
Proceedings of the 16th Asian Conference on Machine Learning, PMLR 260:750-764, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v260-tan25b, title = {Improve Diverse Commonsense Generation by Enhancing Subgraphs}, author = {Tan, Jianman and Yang, Shuo}, booktitle = {Proceedings of the 16th Asian Conference on Machine Learning}, pages = {750--764}, year = {2025}, editor = {Nguyen, Vu and Lin, Hsuan-Tien}, volume = {260}, series = {Proceedings of Machine Learning Research}, month = {05--08 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v260/main/assets/tan25b/tan25b.pdf}, url = {https://proceedings.mlr.press/v260/tan25b.html}, 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.} }
Endnote
%0 Conference Paper %T Improve Diverse Commonsense Generation by Enhancing Subgraphs %A Jianman Tan %A Shuo Yang %B Proceedings of the 16th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Vu Nguyen %E Hsuan-Tien Lin %F pmlr-v260-tan25b %I PMLR %P 750--764 %U https://proceedings.mlr.press/v260/tan25b.html %V 260 %X 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.
APA
Tan, J. & Yang, S.. (2025). Improve Diverse Commonsense Generation by Enhancing Subgraphs. Proceedings of the 16th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 260:750-764 Available from https://proceedings.mlr.press/v260/tan25b.html.

Related Material