Self-Supervised Test-Time Learning for Reading Comprehension

• URL: http://arxiv.org/abs/2103.11263v1
• Date: Sat, 20 Mar 2021 23:24:51 GMT
• Title: Self-Supervised Test-Time Learning for Reading Comprehension
• Authors: Pratyay Banerjee, Tejas Gokhale, Chitta Baral
• Abstract summary: We present a method that performs "test-time learning" (TTL) on a given context (text passage) without requiring training on large-scale human-authored datasets containing textit-question-answer triplets. This method operates directly on a single test context, uses self-supervision to train models on synthetically generated question-answer pairs, and then infers answers to unseen human-authored questions for this context. Our method achieves accuracies competitive with fully supervised methods and significantly outperforms current unsupervised methods.
• Score: 25.814648527497628
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent work on unsupervised question answering has shown that models can be trained with procedurally generated question-answer pairs and can achieve performance competitive with supervised methods. In this work, we consider the task of unsupervised reading comprehension and present a method that performs "test-time learning" (TTL) on a given context (text passage), without requiring training on large-scale human-authored datasets containing \textit{context-question-answer} triplets. This method operates directly on a single test context, uses self-supervision to train models on synthetically generated question-answer pairs, and then infers answers to unseen human-authored questions for this context. Our method achieves accuracies competitive with fully supervised methods and significantly outperforms current unsupervised methods. TTL methods with a smaller model are also competitive with the current state-of-the-art in unsupervised reading comprehension.

Related papers

• Chain of Methodologies: Scaling Test Time Computation without Training [77.85633949575046]
  Large Language Models (LLMs) often struggle with complex reasoning tasks due to insufficient in-depth insights in their training data.<n>This paper introduces the Chain of the (CoM) framework that enhances structured thinking by integrating human methodological insights.
  arXiv  Detail & Related papers  (2025-06-08T03:46:50Z)
• Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning [50.26965628047682]
  Adapting pre-trained models to open classes is a challenging problem in machine learning. In this paper, we consider combining the advantages of both and come up with a test-time prompt tuning approach. Our proposed method outperforms all comparison methods on average considering both base and new classes.
  arXiv  Detail & Related papers  (2024-08-29T12:34:01Z)
• Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning [85.66907881270785]
  We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
  arXiv  Detail & Related papers  (2024-01-07T18:12:20Z)
• Auto-ICL: In-Context Learning without Human Supervision [93.05202223767463]
  We propose Automatic In-Context Learning framework that enables the model to autonomously generate examples and instructions for problem-solving. With experiments across various models and datasets, results show that model-generated contexts outperform human-annotated contexts.
  arXiv  Detail & Related papers  (2023-11-15T07:37:28Z)
• Understanding prompt engineering may not require rethinking generalization [56.38207873589642]
  We show that the discrete nature of prompts, combined with a PAC-Bayes prior given by a language model, results in generalization bounds that are remarkably tight by the standards of the literature. This work provides a possible justification for the widespread practice of prompt engineering.
  arXiv  Detail & Related papers  (2023-10-06T00:52:48Z)
• Test-Time Adaptation with Perturbation Consistency Learning [32.58879780726279]
  We propose a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts. Our method can achieve higher or comparable performance with less inference time over strong PLM backbones.
  arXiv  Detail & Related papers  (2023-04-25T12:29:22Z)
• Momentum Contrastive Pre-training for Question Answering [54.57078061878619]
  MCROSS introduces a momentum contrastive learning framework to align the answer probability between cloze-like and natural query-passage sample pairs. Our method achieves noticeable improvement compared with all baselines in both supervised and zero-shot scenarios.
  arXiv  Detail & Related papers  (2022-12-12T08:28:22Z)
• Semantic Borrowing for Generalized Zero-Shot Learning [0.0]
  Generalized zero-shot learning (GZSL) is one of the most realistic problems, but also one of the most challenging. Instance-borrowing methods and methods solve this problem to some extent with the help of testing semantics. A novel method called Semantic Borrowing for improving GZSL methods with compatibility metric learning under CIII is proposed in this paper.
  arXiv  Detail & Related papers  (2021-01-30T12:14:28Z)
• Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection [80.68446022994492]
  In this work, we explore the unsupervised learning paradigm which can potentially work with unlabeled text corpora. Our model builds upon the recent work on Noisy Student Training, a semi-supervised learning approach that extends the idea of self-training.
  arXiv  Detail & Related papers  (2020-10-29T05:29:26Z)

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.