# Improving Question Answering by Commonsense-Based Pre-Training

Source: [Improving Question Answering by Commonsense-Based Pre-Training](<https://www.sota2.com/research/paper/68fa656f1e209131cea0a5d9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:27:45.299Z

Authors: Wanjun Zhong, Duyu Tang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

Published: 2018-09-05T13:04:56.000Z

## Abstract

Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge. We believe the main reason is the lack of commonsense \\mbox{connections} between concepts. To remedy this, we provide a simple and effective method that leverages external commonsense knowledge base such as ConceptNet. We pre-train direct and indirect relational functions between concepts, and show that these pre-trained functions could be easily added to existing neural network models. Results show that incorporating commonsense-based function improves the baseline on three question answering tasks that require commonsense reasoning. Further analysis shows that our system \\mbox{discovers} and leverages useful evidence from an external commonsense knowledge base, which is missing in existing neural network models and help derive the correct answer.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1809.03568>)

[PDF](<https://arxiv.org/pdf/1809.03568.pdf>)