paper-with-me

Papers

QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization

2019-08-31 · IJCNLP 2019 11 · Yi-Ting Yeh, Yun-Nung Chen

Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but do not actually answer the question. To address this problem, we propose QAInfomax as a regularizer in reading comprehension systems by maximizing mutual information among passages, a question, and its answer. QAInfomax helps regularize the model to not simply learn the superficial correlation for answering questions. The experiments show that our proposed QAInfomax achieves the state-of-the-art performance on the benchmark Adversarial-SQuAD dataset.

📄 PDF Abstract BibTeX arXiv:1909.00215

Code (1)

MiuLab/QAInfomax 공식 구현 pytorch

Tasks

Question AnsweringReading Comprehension

Similar Papers 제목 키워드 기반

Dual Capsule Attention Mask Network with Mutual Learning for Visual Question Answering

2022-10-01 · COLING 2022 10 · Weidong Tian, Haodong Li, Zhong-Qiu Zhao

A Visual Question Answering (VQA) model processes images and questions simultaneously with rich semantic information. The attention mechanism can highlight fine-grained features with critical information, thus ensuring t…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering

2021-06-14 · ACL 2021 5 · Zhihong Shao, Lifeng Shang, Qun Liu, Minlie Huang

Weakly supervised question answering usually has only the final answers as supervision signals while the correct solutions to derive the answers are not provided. This setting gives rise to the spurious solution problem:…

Question Answering

SemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering

2022-07-01 · SemEval (NAACL) 2022 7 · Jingxuan Tu, Eben Holderness, Marco Maru, Simone Conia 외

In this task, we identify a challenge that is reflective of linguistic and cognitive competencies that humans have when speaking and reasoning. Particularly, given the intuition that textual and visual information mutual…

Question Answering

MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension

2021-03-08 · Wei Peng, Yue Hu, Jing Yu, Luxi Xing 외

Question answering systems usually use keyword searches to retrieve potential passages related to a question, and then extract the answer from passages with the machine reading comprehension methods. However, many questi…

Machine Reading ComprehensionQuestion AnsweringReading ComprehensionRelation+1

Sequential Attention with Keyword Mask Model for Community-based Question Answering

2019-06-01 · NAACL 2019 6 · Jianxin Yang, Wenge Rong, Libin Shi, Zhang Xiong

In Community-based Question Answering system(CQA), Answer Selection(AS) is a critical task, which focuses on finding a suitable answer within a list of candidate answers. For neural network models, the key issue is how t…

Answer SelectionQuestion Answering