Improve Diverse Commonsense Generation by Enhancing Subgraphs

Jianman Tan, Shuo Yang

Keywords: Commonsense reasoning, Knowledge graph pruning, Concept expansion

Verify Author List: I have double-checked the author list and understand that additions and removals will not be allowed after the submission deadline.

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 taskrelevant 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.

Primary Area: Applications (bioinformatics, biomedical informatics, climate science, collaborative filtering, computer vision, healthcare, human activity recognition, information retrieval, natural language processing, social networks, etc.)

Paper Checklist Guidelines: I certify that all co-authors of this work have read and commit to adhering to the guidelines in Call for Papers.

Student Author: Yes

Submission Number: 219