Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading

Abstract

This paper aims at improving how machines can answer questions directly from text, with the focus of having models that can answer correctly multiple types of questions and from various types of texts, documents or even from large collections of them. To that end, we introduce the Weaver model that uses a new way to relate a question to a textual context by weaving layers of recurrent networks, with the goal of making as few assumptions as possible as to how the information from both question and context should be combined to form the answer. We show empirically on six datasets that Weaver performs well in multiple conditions. For instance, it produces solid results on the very popular SQuAD dataset (Rajpurkar et al., 2016), solves almost all bAbI tasks (Weston et al., 2015) and greatly outperforms state-of-the-art methods for open domain question answering from text (Chen et al., 2017).

References in corpus (11)

• Teaching Machines to Read and Comprehend
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Adversarial Examples for Evaluating Reading Comprehension Systems
• FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• Query-Reduction Networks for Question Answering
• Stochastic Answer Networks for Machine Reading Comprehension
• Phase Conductor on Multi-layered Attentions for Machine Comprehension

Cited by in corpus (11)

• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Accelerating Real-Time Question Answering via Question Generation
• Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
• A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets
• EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System
• Revisiting the Open-Domain Question Answering Pipeline
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
• Exploiting Sentence Embedding for Medical Question Answering