QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation

• URL: http://arxiv.org/abs/2210.10861v1
• Date: Wed, 19 Oct 2022 19:52:57 GMT
• Title: QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
• Authors: Zhenrui Yue, Huimin Zeng, Bernhard Kratzwald, Stefan Feuerriegel, Dong Wang
• Abstract summary: Question answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. We propose a novel self-supervised framework called QADA for QA domain adaptation.
• Score: 24.39026345750824
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Question answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this paper, we propose a novel self-supervised framework called QADA for QA domain adaptation. QADA introduces a novel data augmentation pipeline used to augment training QA samples. Different from existing methods, we enrich the samples via hidden space augmentation. For questions, we introduce multi-hop synonyms and sample augmented token embeddings with Dirichlet distributions. For contexts, we develop an augmentation method which learns to drop context spans via a custom attentive sampling strategy. Additionally, contrastive learning is integrated in the proposed self-supervised adaptation framework QADA. Unlike existing approaches, we generate pseudo labels and propose to train the model via a novel attention-based contrastive adaptation method. The attention weights are used to build informative features for discrepancy estimation that helps the QA model separate answers and generalize across source and target domains. To the best of our knowledge, our work is the first to leverage hidden space augmentation and attention-based contrastive adaptation for self-supervised domain adaptation in QA. Our evaluation shows that QADA achieves considerable improvements on multiple target datasets over state-of-the-art baselines in QA domain adaptation.

Related papers

• Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection [82.65760006883248]
  We introduce a new task named Change Detection Question Answering and Grounding (CDQAG) CDQAG extends the traditional change detection task by providing interpretable textual answers and intuitive visual evidence. Based on this, we present VisTA, a simple yet effective baseline method that unifies the tasks of question answering and grounding.
  arXiv  Detail & Related papers  (2024-10-31T11:20:13Z)
• KaPQA: Knowledge-Augmented Product Question-Answering [59.096607961704656]
  We introduce two product question-answering (QA) datasets focused on Adobe Acrobat and Photoshop products. We also propose a novel knowledge-driven RAG-QA framework to enhance the performance of the models in the product QA task.
  arXiv  Detail & Related papers  (2024-07-22T22:14:56Z)
• Closed-book Question Generation via Contrastive Learning [20.644215991166895]
  We propose a new QG model empowered by a contrastive learning module and an answer reconstruction module. We show how to leverage the proposed model to improve existing closed-book QA systems.
  arXiv  Detail & Related papers  (2022-10-13T06:45:46Z)
• Domain Adaptation for Question Answering via Question Classification [8.828396559882954]
  We propose a novel framework: Question Classification for Question Answering (QC4QA) For optimization, inter-domain discrepancy between the source and target domain is reduced via maximum mean discrepancy (MMD) distance. We demonstrate the effectiveness of the proposed QC4QA with consistent improvements against the state-of-the-art baselines on multiple datasets.
  arXiv  Detail & Related papers  (2022-09-12T03:12:02Z)
• Prior Knowledge Guided Unsupervised Domain Adaptation [82.9977759320565]
  We propose a Knowledge-guided Unsupervised Domain Adaptation (KUDA) setting where prior knowledge about the target class distribution is available. In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound and Binary Relationship. We propose a rectification module that uses such prior knowledge to refine model generated pseudo labels.
  arXiv  Detail & Related papers  (2022-07-18T18:41:36Z)
• Synthetic Question Value Estimation for Domain Adaptation of Question Answering [31.003053719921628]
  We introduce a novel idea of training a question value estimator (QVE) that directly estimates the usefulness of synthetic questions for improving the target-domain QA performance. By using such questions and only around 15% of the human annotations on the target domain, we can achieve comparable performance to the fully-supervised baselines.
  arXiv  Detail & Related papers  (2022-03-16T20:22:31Z)
• Domain-robust VQA with diverse datasets and methods but no target labels [34.331228652254566]
  Domain adaptation for VQA differs from adaptation for object recognition due to additional complexity. To tackle these challenges, we first quantify domain shifts between popular VQA datasets. We also construct synthetic shifts in the image and question domains separately.
  arXiv  Detail & Related papers  (2021-03-29T22:24:50Z)
• MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering [58.30291671877342]
  We present MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input. MUTANT establishes a new state-of-the-art accuracy on VQA-CP with a $10.57%$ improvement.
  arXiv  Detail & Related papers  (2020-09-18T00:22:54Z)
• Knowledge Graph Simple Question Answering for Unseen Domains [9.263766921991452]
  We propose a data-centric domain adaptation framework that is applicable to new domains. We use distant supervision to extract a set of keywords that express each relation of the unseen domain. Our framework significantly improves over zero-shot baselines and is robust across domains.
  arXiv  Detail & Related papers  (2020-05-25T11:34:54Z)
• Harvesting and Refining Question-Answer Pairs for Unsupervised QA [95.9105154311491]
  We introduce two approaches to improve unsupervised Question Answering (QA) First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA) Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA.
  arXiv  Detail & Related papers  (2020-05-06T15:56:06Z)
• Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering [98.48363619128108]
  We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sentence improves downstream QA performance.
  arXiv  Detail & Related papers  (2020-04-24T17:57:45Z)

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.