# A Semantic-based Method for Unsupervised Commonsense Question Answering

arXiv: https://arxiv.org/abs/2105.14781 · HTML: https://mlsanity.com/paper/2105.14781/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering](https://mlsanity.com/paper/2005.00691/) (2020)
- [Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning](https://mlsanity.com/paper/2004.14074/) (2020)
- [A Surprisingly Robust Trick for Winograd Schema Challenge](https://mlsanity.com/paper/1905.06290/) (2019)
- [Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering](https://mlsanity.com/paper/2005.00316/) (2020)
- [The Sensitivity of Language Models and Humans to Winograd Schema Perturbations](https://mlsanity.com/paper/2005.01348/) (2020)
- [Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering](https://mlsanity.com/paper/1911.03876/) (2019)
- [Unsupervised Deep Structured Semantic Models for Commonsense Reasoning](https://mlsanity.com/paper/1904.01938/) (2019)
- [COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering](https://mlsanity.com/paper/2011.00777/) (2020)

## Built on by (most cited first, 10 of 10)

- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models](https://mlsanity.com/paper/2303.16421/) (2023)
- [Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2201.12438/) (2022)
- [Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models](https://mlsanity.com/paper/2205.01841/) (2022)
- [Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering](https://mlsanity.com/paper/2305.05936/) (2023)
- [TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering](https://mlsanity.com/paper/2211.13515/) (2022)
- [ArT: All-round Thinker for Unsupervised Commonsense Question-Answering](https://mlsanity.com/paper/2112.13428/) (2021)
- [BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering](https://mlsanity.com/paper/2305.15932/) (2023)
- [Evaluate Confidence Instead of Perplexity for Zero-shot Commonsense Reasoning](https://mlsanity.com/paper/2208.11007/) (2022)
- [CASE: Commonsense-Augmented Score with an Expanded Answer Space](https://mlsanity.com/paper/2311.01684/) (2023)

## Abstract (arXiv)

Unsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language models to score candidate choices directly conditioned on the question or context. However, such scores from language models can be easily affected by irrelevant factors, such as word frequencies, sentence structures, etc. These distracting factors may not only mislead the model to choose a wrong answer but also make it oversensitive to lexical perturbations in candidate answers. In this paper, we present a novel SEmantic-based Question Answering method (SEQA) for unsupervised commonsense question answering. Instead of directly scoring each answer choice, our method first generates a set of plausible answers with generative models (e.g., GPT-2), and then uses these plausible answers to select the correct choice by considering the semantic similarity between each plausible answer and each choice. We devise a simple, yet sound formalism for this idea and verify its effectiveness and robustness with extensive experiments. We evaluate the proposed method on four benchmark datasets, and our method achieves the best results in unsupervised settings. Moreover, when attacked by TextFooler with synonym replacement, SEQA demonstrates much less performance drops than baselines, thereby indicating stronger robustness.