Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering
Preprint
Abstract
Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the properties of retrieved knowledge, they still have trouble benefiting from both the knowledge relevance and distinguishment simultaneously. To address the challenge, we propose CPACE, a Concept-centric Prompt-bAsed Contrastive Explanation Generation model, which aims to convert obtained symbolic knowledge into a contrastive explanation for better distinguishing the differences among given candidates. Firstly, following previous works, we retrieve different types of symbolic knowledge with a concept-centric knowledge extraction module. After that, we generate corresponding contrastive explanations using acquired symbolic knowledge and explanation prompts as guidance for better modeling the knowledge distinguishment and interpretability. Finally, we regard the generated contrastive explanation as external knowledge for downstream task enhancement. We conduct a series of experiments on three widely-used question-answering datasets: CSQA, QASC, and OBQA. Experimental results demonstrate that with the help of generated contrastive explanation, our CPACE model achieves new SOTA on CSQA (89.8% on the testing set, 0.9% higher than human performance), and gains impressive improvement on QASC and OBQA (4.2% and 3.5%, respectively).Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language RepresentationTransactions of the Association for Computational Linguistics, 2021
- Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources2020
- Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering2020
- CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning2020
- Unsupervised Commonsense Question Answering with Self-Talk2020
- How Much Knowledge Can You Pack Into the Parameters of a Language Model?2020
- ALICE: Active Learning with Contrastive Natural Language Explanations2020
- Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering2020