MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
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.
PDF Abstract
SQuAD
TriviaQA
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Question Answering | SQuAD1.1 | MEMEN (single model) | EM | 78.234 | # 91 | |
| F1 | 85.344 | # 99 | ||||
| Question Answering | SQuAD1.1 | MEMEN (ensemble) | EM | 75.370 | # 119 | |
| F1 | 82.658 | # 131 | ||||
| Question Answering | SQuAD1.1 | MEMEN (single model) | EM | 78.234 | # 91 | |
| F1 | 85.344 | # 99 | ||||
| Question Answering | TriviaQA | MEMEN | EM | 43.16 | # 37 | |
| F1 | 46.90 | # 10 |
