Smarnet: Teaching Machines to Read and Comprehend Like Human
arXiv:1710.02772
Abstract
Machine Comprehension (MC) is a challenging task in Natural Language Processing field, which aims to guide the machine to comprehend a passage and answer the given question. Many existing approaches on MC task are suffering the inefficiency in some bottlenecks, such as insufficient lexical understanding, complex question-passage interaction, incorrect answer extraction and so on. In this paper, we address these problems from the viewpoint of how humans deal with reading tests in a scientific way. Specifically, we first propose a novel lexical gating mechanism to dynamically combine the words and characters representations. We then guide the machines to read in an interactive way with attention mechanism and memory network. Finally we add a checking layer to refine the answer for insurance. The extensive experiments on two popular datasets SQuAD and TriviaQA show that our method exceeds considerable performance than most state-of-the-art solutions at the time of submission.
arXiv comment8 pages, paper for SQuAD machine comprehension
References in corpus (12)
- ADADELTA: An Adaptive Learning Rate Method
- NLTK: The Natural Language Toolkit
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- 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
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- Reading Wikipedia to Answer Open-Domain Questions
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- Structural Embedding of Syntactic Trees for Machine Comprehension
- Ruminating Reader: Reasoning with Gated Multi-Hop Attention
Cited by in corpus (7)
- Neural Machine Reading Comprehension: Methods and Trends
- The Effect of Natural Distribution Shift on Question Answering Models
- Making Neural Machine Reading Comprehension Faster
- Integrated Triaging for Fast Reading Comprehension
- Multi-Mention Learning for Reading Comprehension with Neural Cascades
- Deep Understanding based Multi-Document Machine Reading Comprehension
- An Understanding-Oriented Robust Machine Reading Comprehension Model