A Semantic-based Method for Unsupervised Commonsense Question Answering

05/31/2021
by   Yilin Niu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2022

TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering

Unsupervised commonsense question answering requires mining effective co...
research
05/25/2023

BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering

Unsupervised commonsense reasoning (UCR) is becoming increasingly popula...
research
12/26/2021

ArT: All-round Thinker for Unsupervised Commonsense Question-Answering

Without labeled question-answer pairs for necessary training, unsupervis...
research
04/22/2019

SocialIQA: Commonsense Reasoning about Social Interactions

We introduce SocialIQa, the first large-scale benchmark for commonsense ...
research
10/29/2022

Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering

We propose a simple refactoring of multi-choice question answering (MCQA...
research
08/17/2023

Semantic Consistency for Assuring Reliability of Large Language Models

Large Language Models (LLMs) exhibit remarkable fluency and competence a...
research
11/01/2020

Generating Correct Answers for Progressive Matrices Intelligence Tests

Raven's Progressive Matrices are multiple-choice intelligence tests, whe...

Please sign up or login with your details

Forgot password? Click here to reset