QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization
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.
Code (1)
Tasks
Question AnsweringReading ComprehensionSimilar Papers 제목 키워드 기반
Dual Capsule Attention Mask Network with Mutual Learning for Visual Question Answering
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
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 AnsweringSemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering
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 AnsweringMCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension
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+1Sequential Attention with Keyword Mask Model for Community-based Question Answering
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