Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation

TL;DR

Gotta introduces a prompt-based data augmentation framework using cloze tasks to improve few-shot question answering by enhancing model reasoning and leveraging prompt-tuning, leading to superior performance on benchmark datasets.

Contribution

The paper proposes a novel prompt-tuning-based cloze data augmentation method that integrates reasoning tasks into few-shot QA, improving performance and understanding.

Findings

Gotta outperforms baseline models on multiple benchmarks.

Prompt-based auxiliary tasks enhance reasoning in few-shot QA.

Prompt-tuning effectively guides model learning in low-data scenarios.

Abstract

Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available. Although existing studies have made some progress and can usually achieve proper results, they suffer from understanding deep semantics for reasoning out the questions. In this paper, we develop Gotta, a Generative prOmpT-based daTa Augmentation framework to mitigate the challenge above. Inspired by the human reasoning process, we propose to integrate the cloze task to enhance few-shot QA learning. Following the recent success of prompt-tuning, we present the cloze task in the same format as the main QA task, allowing the model to learn both tasks seamlessly together to fully take advantage of the power of prompt-tuning. Extensive experiments on widely used benchmarks demonstrate that Gotta consistently outperforms competitive baselines, validating the effectiveness of our proposed prompt-tuning-based cloze task, which not only fine-tunes language models but also learns to guide reasoning in QA tasks. Further analysis shows that the prompt-based loss incorporates the auxiliary task better than the multi-task loss, highlighting the strength of prompt-tuning on the few-shot QA task.