MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension

Abstract

Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and name entity of the words, which are very crucial to the quality of encoding. Moreover, existing attention methods represent each query word as a vector or use a single vector to represent the whole query sentence, neither of them can handle the proper weight of the key words in query sentence. In this paper, we introduce a novel neural network architecture called Multi-layer Embedding with Memory Network(MEMEN) for machine reading task. In the encoding layer, we employ classic skip-gram model to the syntactic and semantic information of the words to train a new kind of embedding layer. We also propose a memory network of full-orientation matching of the query and passage to catch more pivotal information. Experiments show that our model has competitive results both from the perspectives of precision and efficiency in Stanford Question Answering Dataset(SQuAD) among all published results and achieves the state-of-the-art results on TriviaQA dataset.

References in corpus (4)

• ADADELTA: An Adaptive Learning Rate Method
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Multi-Perspective Context Matching for Machine Comprehension
• Who did What: A Large-Scale Person-Centered Cloze Dataset

Cited by in corpus (5)

• Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
• Phase Conductor on Multi-layered Attentions for Machine Comprehension
• Smarnet: Teaching Machines to Read and Comprehend Like Human
• Neural Skill Transfer from Supervised Language Tasks to Reading Comprehension
• Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation