# Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths

arXiv: https://arxiv.org/abs/2009.11753 · HTML: https://mlsanity.com/paper/2009.11753/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [A Survey of Knowledge Enhanced Pre-trained Language Models](https://mlsanity.com/paper/2211.05994/) (2022)
- [NormBank: A Knowledge Bank of Situational Social Norms](https://mlsanity.com/paper/2305.17008/) (2023)
- [Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2201.12438/) (2022)
- [Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring](https://mlsanity.com/paper/2106.06719/) (2021)
- [Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks](https://mlsanity.com/paper/2105.05457/) (2021)
- [Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations](https://mlsanity.com/paper/2106.13876/) (2021)
- [Semantic Categorization of Social Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/2109.05168/) (2021)
- [Open-ended Commonsense Reasoning with Unrestricted Answer Scope](https://mlsanity.com/paper/2310.11672/) (2023)

## Abstract (arXiv)

Commonsense explanation generation aims to empower the machine's sense-making capability by generating plausible explanations to statements against commonsense. While this task is easy to human, the machine still struggles to generate reasonable and informative explanations. In this work, we propose a method that first extracts the underlying concepts which are served as textitbridges in the reasoning chain and then integrates these concepts to generate the final explanation. To facilitate the reasoning process, we utilize external commonsense knowledge to build the connection between a statement and the bridge concepts by extracting and pruning multi-hop paths to build a subgraph. We design a bridge concept extraction model that first scores the triples, routes the paths in the subgraph, and further selects bridge concepts with weak supervision at both the triple level and the concept level. We conduct experiments on the commonsense explanation generation task and our model outperforms the state-of-the-art baselines in both automatic and human evaluation.