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

• URL: http://arxiv.org/abs/2306.04101v1
• Date: Wed, 7 Jun 2023 01:44:43 GMT
• Title: Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation
• Authors: Xiusi Chen, Yu Zhang, Jinliang Deng, Jyun-Yu Jiang, Wei Wang
• Abstract summary: Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages. We develop Gotta, a Generative prOmpT-based daTa Augmentation framework. Inspired by the human reasoning process, we propose to integrate the cloze task to enhance few-shot QA learning.
• Score: 18.531941086922256
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer [76.39111896665585]
  Incremental Learning (IL) aims to learn deep models on sequential tasks continually. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples.
  arXiv  Detail & Related papers  (2024-07-04T10:37:58Z)
• Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks [101.40633115037983]
  Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. How to select new tasks to improve the performance and generalizability of IT models remains an open question. We propose active instruction tuning based on prompt uncertainty, a novel framework to identify informative tasks, and then actively tune the models on the selected tasks.
  arXiv  Detail & Related papers  (2023-11-01T04:40:05Z)
• Active Prompting with Chain-of-Thought for Large Language Models [26.5029080638055]
  This paper proposes a new method, Active-Prompt, to adapt large language models to different tasks. By borrowing ideas from the related problem of uncertainty-based active learning, we introduce several metrics to characterize the uncertainty. Experimental results demonstrate the superiority of our proposed method, achieving state-of-the-art on eight complex reasoning tasks.
  arXiv  Detail & Related papers  (2023-02-23T18:58:59Z)
• Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering [28.809665884372183]
  Experimental results on 2WikiMultiHopQA and HotpotQA-small datasets reveal that (1) UR tasks can improve QA performance. We find that (3) UR tasks do not contribute to improving the robustness of the model on adversarial questions, such as sub-questions and inverted questions.
  arXiv  Detail & Related papers  (2023-02-12T17:32:55Z)
• Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization [89.04537372465612]
  Socratic pretraining is a question-driven, unsupervised pretraining objective designed to improve controllability in summarization tasks. Our results show that Socratic pretraining cuts task-specific labeled data requirements in half.
  arXiv  Detail & Related papers  (2022-12-20T17:27:10Z)
• Rethinking Label Smoothing on Multi-hop Question Answering [87.68071401870283]
  Multi-Hop Question Answering (MHQA) is a significant area in question answering. In this work, we analyze the primary factors limiting the performance of multi-hop reasoning. We propose a novel label smoothing technique, F1 Smoothing, which incorporates uncertainty into the learning process.
  arXiv  Detail & Related papers  (2022-12-19T14:48:08Z)
• Task Compass: Scaling Multi-task Pre-training with Task Prefix [122.49242976184617]
  Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. We propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. Our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships.
  arXiv  Detail & Related papers  (2022-10-12T15:02:04Z)
• Continuous QA Learning with Structured Prompts [20.246786740364133]
  Diana is a dynamic architecture-based lifelong QA model that tries to learn a sequence of QA tasks. Four types of hierarchically organized prompts are used in Diana to capture QA knowledge from different granularities. In experiments, Diana outperforms state-of-the-art lifelong QA models, especially in handling unseen tasks.
  arXiv  Detail & Related papers  (2022-08-31T02:38:16Z)
• ProQA: Structural Prompt-based Pre-training for Unified Question Answering [84.59636806421204]
  ProQA is a unified QA paradigm that solves various tasks through a single model. It concurrently models the knowledge generalization for all QA tasks while keeping the knowledge customization for every specific QA task. ProQA consistently boosts performance on both full data fine-tuning, few-shot learning, and zero-shot testing scenarios.
  arXiv  Detail & Related papers  (2022-05-09T04:59:26Z)
• Embedding Adaptation is Still Needed for Few-Shot Learning [25.4156194645678]
  ATG is a principled clustering method to defining train and test tasksets without additional human knowledge. We empirically demonstrate the effectiveness of ATG in generating tasksets that are easier, in-between, or harder than existing benchmarks. We leverage our generated tasksets to shed a new light on few-shot classification: gradient-based methods can outperform metric-based ones when transfer is most challenging.
  arXiv  Detail & Related papers  (2021-04-15T06:00:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.