How Additional Knowledge can Improve Natural Language Commonsense Question Answering?

Abstract

Recently several datasets have been proposed to encourage research in Question Answering domains where commonsense knowledge is expected to play an important role. Recent language models such as ROBERTA, BERT and GPT that have been pre-trained on Wikipedia articles and books have shown reasonable performance with little fine-tuning on several such Multiple Choice Question-Answering (MCQ) datasets. Our goal in this work is to develop methods to incorporate additional (commonsense) knowledge into language model-based approaches for better question-answering in such domains. In this work, we first categorize external knowledge sources, and show performance does improve on using such sources. We then explore three different strategies for knowledge incorporation and four different models for question-answering using external commonsense knowledge. We analyze our predictions to explore the scope of further improvements.

arXiv comment14 pages, 14 figures, 3 tables

References in corpus (5)

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Neural Natural Language Inference Models Enhanced with External Knowledge
• WikiHow: A Large Scale Text Summarization Dataset
• A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories
• Abductive Commonsense Reasoning

Cited by in corpus (9)

• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
• Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
• Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks
• Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering
• Natural Language QA Approaches using Reasoning with External Knowledge
• Knowledge Guided Named Entity Recognition for BioMedical Text
• Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense
• Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks
• Development of User-friendly Smart Grid Architecture