End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension

Abstract

This paper proposes dynamic chunk reader (DCR), an end-to-end neural reading comprehension (RC) model that is able to extract and rank a set of answer candidates from a given document to answer questions. DCR is able to predict answers of variable lengths, whereas previous neural RC models primarily focused on predicting single tokens or entities. DCR encodes a document and an input question with recurrent neural networks, and then applies a word-by-word attention mechanism to acquire question-aware representations for the document, followed by the generation of chunk representations and a ranking module to propose the top-ranked chunk as the answer. Experimental results show that DCR achieves state-of-the-art exact match and F1 scores on the SQuAD dataset.

Submitted to AAAI

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Attentive Pooling Networks
• Reinforcement Learning Neural Turing Machines - Revised
• Learning Natural Language Inference with LSTM
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
• Consensus Attention-based Neural Networks for Chinese Reading Comprehension
• A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
• Separating Answers from Queries for Neural Reading Comprehension
• Attention-Based Convolutional Neural Network for Machine Comprehension
• Structured Memory for Neural Turing Machines
• Empirical Study on Deep Learning Models for Question Answering

Cited by in corpus (18)

• Dynamic Coattention Networks For Question Answering
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Multi-Perspective Context Matching for Machine Comprehension
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• A Unified Query-based Generative Model for Question Generation and Question Answering
• S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
• Words or Characters? Fine-grained Gating for Reading Comprehension
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• A Comparative Study of Word Embeddings for Reading Comprehension
• Neural Machine Reading Comprehension: Methods and Trends
• The Effect of Natural Distribution Shift on Question Answering Models
• Improving Background Based Conversation with Context-aware Knowledge Pre-selection
• Structural Embedding of Syntactic Trees for Machine Comprehension
• Ruminating Reader: Reasoning with Gated Multi-Hop Attention
• Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
• Curriculum Learning Strategies for IR: An Empirical Study on Conversation Response Ranking
• CAESAR: Context Awareness Enabled Summary-Attentive Reader