Reasoning with Memory Augmented Neural Networks for Language Comprehension

2016/10/20 by Tsendsuren Munkhdalai, Hong Yu, Munkhdalai, Tsendsuren +1 · 1 citation
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (stat.ML) #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Topic Modeling #cs.AI #cs.CL #cs.NE #stat.ML

paper · pdf · doi:10.48550/arxiv.1610.06454

Accepted at ICLR 2017

openalex publication_date 2016/10/20 · arxiv created 2017/02/28 · arxiv updated 2017/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Hypothesis testing is an important cognitive process that supports human reasoning. In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks. Our approach involves a hypothesis testing loop that reconsiders and progressively refines a previously formed hypothesis in order to generate new hypotheses to test. We apply the proposed approach to language comprehension task by using Neural Semantic Encoders (NSE). Our NSE models achieve the state-of-the-art results showing an absolute improvement of 1.2% to 2.6% accuracy over previous results obtained by single and ensemble systems on standard machine comprehension benchmarks such as the Children's Book Test (CBT) and Who-Did-What (WDW) news article datasets.

Cited by

• Effective Character-augmented Word Embedding for Machine Reading Comprehension

Related

• Neural Semantic Encoders
• Deep Learning Models to Study Sentence Comprehension in the Human Brain
• Probing Neural Network Comprehension of Natural Language Arguments
• Sentence Simplification with Memory-Augmented Neural Networks
• Stress-Testing Neural Models of Natural Language Inference with Multiply-Quantified Sentences