U-Net: Machine Reading Comprehension with Unanswerable Questions

Abstract

Machine reading comprehension with unanswerable questions is a new challenging task for natural language processing. A key subtask is to reliably predict whether the question is unanswerable. In this paper, we propose a unified model, called U-Net, with three important components: answer pointer, no-answer pointer, and answer verifier. We introduce a universal node and thus process the question and its context passage as a single contiguous sequence of tokens. The universal node encodes the fused information from both the question and passage, and plays an important role to predict whether the question is answerable and also greatly improves the conciseness of the U-Net. Different from the state-of-art pipeline models, U-Net can be learned in an end-to-end fashion. The experimental results on the SQuAD 2.0 dataset show that U-Net can effectively predict the unanswerability of questions and achieves an F1 score of 71.7 on SQuAD 2.0.

arXiv comment9 pages

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Teaching Machines to Read and Comprehend
• Densely Connected Convolutional Networks
• Bidirectional Attention Flow for Machine Comprehension
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• Dynamic Coattention Networks For Question Answering
• Machine Comprehension Using Match-LSTM and Answer Pointer
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
• Learning Recurrent Span Representations for Extractive Question Answering
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• Stochastic Answer Networks for Machine Reading Comprehension
• Read + Verify: Machine Reading Comprehension with Unanswerable Questions

Cited by in corpus (11)

• Text Compression-aided Transformer Encoding
• Neural Machine Reading Comprehension: Methods and Trends
• SG-Net: Syntax-Guided Machine Reading Comprehension
• Semantics-aware BERT for Language Understanding
• Multi-style Generative Reading Comprehension
• Improving Machine Reading Comprehension via Adversarial Training
• BERTQA -- Attention on Steroids
• Less is More: Rejecting Unreliable Reviews for Product Question Answering
• Relation Module for Non-answerable Prediction on Question Answering
• EQuANt (Enhanced Question Answer Network)
• MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension